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

Dataset: The Pile

Neuron 1611 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8737. Min Act: -0.0000

Data Index: 224182 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1993478 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.9022. Min Act: -0.0000

Data Index: 659093 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1054783 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1716554 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8244. Min Act: -0.0000

Data Index: 246476 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1450749 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8204. Min Act: -0.0000

Data Index: 700238 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1172552 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7828. Min Act: -0.0000

Data Index: 457477 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1326001 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6425. Min Act: -0.0000

Data Index: 370232 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7897. Min Act: -0.0000

Data Index: 972265 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1072288 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1679055 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1726314 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1734674 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1030426 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1758038 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7696. Min Act: -0.0000

Data Index: 101209 (The Pile)

Max Activating Token Index: 1010