Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1503879 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4146. Min Act: -0.0001

Data Index: 1636350 (Python Code)

Max Activating Token Index: 737

Text #2

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1515207 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1620154 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1644881 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3689. Min Act: -0.0001

Data Index: 1415483 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1412008 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1536795 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1463107 (Python Code)

Max Activating Token Index: 563

Text #9

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1450390 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3541. Min Act: -0.0001

Data Index: 1652006 (Python Code)

Max Activating Token Index: 394

Text #11

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1465854 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1410610 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1409766 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1504273 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3165. Min Act: -0.0001

Data Index: 1514806 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1548502 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1564642 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1629177 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1386697 (Python Code)

Max Activating Token Index: 113