< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 253 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 3.2723. Min Range: -3.2723

Max Act: 3.2723. Min Act: -0.0000

Data Index: 1866661 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.9105. Min Act: -0.0000

Data Index: 1071410 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.5346. Min Act: -0.0000

Data Index: 405344 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.5859. Min Act: -0.0000

Data Index: 1673376 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.6761. Min Act: -0.0000

Data Index: 1188327 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.5701. Min Act: -0.0000

Data Index: 1550288 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.6047. Min Act: -0.0000

Data Index: 1955514 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.3224. Min Act: -0.0000

Data Index: 1380947 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.3566. Min Act: -0.0000

Data Index: 1348993 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.2326. Min Act: -0.0000

Data Index: 1542593 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.3401. Min Act: -0.0000

Data Index: 1521560 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.4325. Min Act: -0.0000

Data Index: 690454 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.2992. Min Act: -0.0000

Data Index: 19907 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.1811. Min Act: -0.0000

Data Index: 615181 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.3206. Min Act: -0.0000

Data Index: 489230 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.3027. Min Act: -0.0000

Data Index: 185716 (The Pile)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.5423. Min Act: -0.0000

Data Index: 764884 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.1573. Min Act: -0.0000

Data Index: 1333845 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.2740. Min Act: -0.0000

Data Index: 1743916 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2723. Min Range: -3.2723

Max Act: 2.1302. Min Act: -0.0000

Data Index: 505203 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #19