< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1279643 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1537776 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2651. Min Act: -0.0001

Data Index: 708909 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2516. Min Act: -0.0001

Data Index: 207212 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1074021 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2637. Min Act: -0.0001

Data Index: 84927 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2501. Min Act: -0.0001

Data Index: 208844 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1744633 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1855388 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2547. Min Act: -0.0001

Data Index: 345427 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2352. Min Act: -0.0001

Data Index: 433497 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1178218 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2328. Min Act: -0.0001

Data Index: 417942 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1545290 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2287. Min Act: -0.0001

Data Index: 519590 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1258356 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2342. Min Act: -0.0001

Data Index: 770269 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2331. Min Act: -0.0001

Data Index: 271242 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2328. Min Act: -0.0001

Data Index: 404111 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2152. Min Act: -0.0001

Data Index: 647284 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #19