< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.5445. Min Act: -0.0001

Data Index: 597916 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4194. Min Act: -0.0001

Data Index: 725514 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4860. Min Act: -0.0001

Data Index: 1383280 (The Pile)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6483. Min Act: -0.0001

Data Index: 397541 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6117. Min Act: -0.0001

Data Index: 1104513 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2620. Min Act: -0.0001

Data Index: 971756 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2198. Min Act: -0.0001

Data Index: 655012 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3437. Min Act: -0.0001

Data Index: 111813 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2580. Min Act: -0.0001

Data Index: 493455 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2972. Min Act: -0.0001

Data Index: 1790227 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4845. Min Act: -0.0001

Data Index: 54100 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.1312. Min Act: -0.0001

Data Index: 191643 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6483. Min Range: -1.6483

Max Act: 0.8881. Min Act: -0.0001

Data Index: 929181 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3169. Min Act: -0.0001

Data Index: 564978 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.1203. Min Act: -0.0001

Data Index: 686868 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2786. Min Act: -0.0001

Data Index: 429566 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2740. Min Act: -0.0001

Data Index: 1259748 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.2583. Min Act: -0.0001

Data Index: 359649 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.1103. Min Act: -0.0001

Data Index: 431456 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.1041. Min Act: -0.0001

Data Index: 1358230 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #19