Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5684 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2945. Min Act: -0.0002

Data Index: 1526915 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2689. Min Act: -0.0002

Data Index: 1656973 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2463. Min Act: -0.0002

Data Index: 592804 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2356. Min Act: -0.0002

Data Index: 1513886 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2343. Min Act: -0.0002

Data Index: 868828 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2305. Min Act: -0.0002

Data Index: 1390940 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2346. Min Act: -0.0002

Data Index: 1352476 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2256. Min Act: -0.0002

Data Index: 422965 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2308. Min Act: -0.0002

Data Index: 1551299 (Python Code)

Max Activating Token Index: 485

Text #9

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2221. Min Act: -0.0002

Data Index: 91690 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2226. Min Act: -0.0002

Data Index: 1272829 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2228. Min Act: -0.0002

Data Index: 368135 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2097. Min Act: -0.0002

Data Index: 1402068 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2139. Min Act: -0.0002

Data Index: 392111 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2081. Min Act: -0.0002

Data Index: 1451495 (Python Code)

Max Activating Token Index: 622

Text #15

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2065. Min Act: -0.0002

Data Index: 171398 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2143. Min Act: -0.0002

Data Index: 1082138 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2063. Min Act: -0.0002

Data Index: 939666 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2120. Min Act: -0.0002

Data Index: 1061806 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2083. Min Act: -0.0002

Data Index: 259338 (C4 (Web Text))

Max Activating Token Index: 498