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

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

Neuron 3840 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9981. Min Range: -6.9981

Max Act: 6.5713. Min Act: -0.0000

Data Index: 560318 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 6.9981. Min Range: -6.9981

Max Act: 6.9981. Min Act: -0.0000

Data Index: 1231264 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.7823. Min Act: -0.0000

Data Index: 1193210 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.7867. Min Act: -0.0000

Data Index: 1346435 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.4253. Min Act: -0.0000

Data Index: 894147 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.4971. Min Act: -0.0000

Data Index: 512421 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.7066. Min Act: -0.0000

Data Index: 1172622 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.2063. Min Act: -0.0000

Data Index: 75294 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 6.9981. Min Range: -6.9981

Max Act: 4.9982. Min Act: -0.0000

Data Index: 915026 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.3676. Min Act: -0.0000

Data Index: 34500 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.2551. Min Act: -0.0000

Data Index: 861289 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.2468. Min Act: -0.0000

Data Index: 762382 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.2045. Min Act: -0.0000

Data Index: 394610 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 6.9981. Min Range: -6.9981

Max Act: 4.9738. Min Act: -0.0000

Data Index: 1224912 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.5323. Min Act: -0.0000

Data Index: 939420 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.2225. Min Act: -0.0000

Data Index: 1109266 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.4139. Min Act: -0.0000

Data Index: 1151972 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 6.9981. Min Range: -6.9981

Max Act: 5.2163. Min Act: -0.0000

Data Index: 733980 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 6.9981. Min Range: -6.9981

Max Act: 4.9924. Min Act: -0.0000

Data Index: 1121462 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 6.9981. Min Range: -6.9981

Max Act: 4.8776. Min Act: -0.0000

Data Index: 143836 (C4 (Web Text))

Max Activating Token Index: 613