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

Dataset: The Pile

Neuron 3503 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: 0.5228. Min Range: -0.5228

Max Act: 0.5228. Min Act: -0.0000

Data Index: 577555 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1774479 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4741. Min Act: -0.0000

Data Index: 967614 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4446. Min Act: -0.0000

Data Index: 181235 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1133379 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4327. Min Act: -0.0000

Data Index: 256920 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4370. Min Act: -0.0000

Data Index: 784495 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4387. Min Act: -0.0000

Data Index: 158411 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1722107 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1082914 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1707165 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4097. Min Act: -0.0000

Data Index: 513941 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1075492 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4192. Min Act: -0.0000

Data Index: 541968 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4299. Min Act: -0.0000

Data Index: 817214 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1196370 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4135. Min Act: -0.0000

Data Index: 313817 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4230. Min Act: -0.0000

Data Index: 225708 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4060. Min Act: -0.0000

Data Index: 640819 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3926. Min Act: -0.0000

Data Index: 454210 (The Pile)

Max Activating Token Index: 874