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

Dataset: The Pile

Neuron 367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1133179 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3885. Min Act: -0.0000

Data Index: 973426 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3577. Min Act: -0.0000

Data Index: 192610 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3260. Min Act: -0.0000

Data Index: 869781 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3074. Min Act: -0.0000

Data Index: 590698 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1663646 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3122. Min Act: -0.0000

Data Index: 868283 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2988. Min Act: -0.0000

Data Index: 147203 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3061. Min Act: -0.0000

Data Index: 249625 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3039. Min Act: -0.0000

Data Index: 264741 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1993790 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2903. Min Act: -0.0000

Data Index: 177521 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1206113 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2881. Min Act: -0.0000

Data Index: 583644 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1664170 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1749939 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1731450 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1123340 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2778. Min Act: -0.0000

Data Index: 347758 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2789. Min Act: -0.0000

Data Index: 472859 (The Pile)

Max Activating Token Index: 258