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

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

Neuron 638 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0002

Data Index: 76136 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0328. Min Act: -0.0002

Data Index: 588902 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0306. Min Act: -0.0002

Data Index: 769208 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1624609 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0258. Min Act: -0.0002

Data Index: 774977 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0255. Min Act: -0.0002

Data Index: 411206 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1183013 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0230. Min Act: -0.0002

Data Index: 185187 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0251. Min Act: -0.0002

Data Index: 194122 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0255. Min Act: -0.0002

Data Index: 545208 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0232. Min Act: -0.0002

Data Index: 404008 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0220. Min Act: -0.0002

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0221. Min Act: -0.0002

Data Index: 557344 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0230. Min Act: -0.0002

Data Index: 292807 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0228. Min Act: -0.0002

Data Index: 75999 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1334713 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1072487 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1225428 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0205. Min Act: -0.0002

Data Index: 573679 (C4 (Web Text))

Max Activating Token Index: 597