Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1241 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0294. Min Act: -0.0005

Data Index: 838947 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0283. Min Act: -0.0005

Data Index: 540897 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0275. Min Act: -0.0005

Data Index: 1261734 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1124775 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0258. Min Act: -0.0005

Data Index: 404358 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0254. Min Act: -0.0005

Data Index: 870745 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0260. Min Act: -0.0005

Data Index: 1033099 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1247720 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0235. Min Act: -0.0005

Data Index: 321240 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0255. Min Act: -0.0005

Data Index: 897131 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0259. Min Act: -0.0005

Data Index: 86888 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0258. Min Act: -0.0005

Data Index: 82620 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1158815 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1542609 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0267. Min Act: -0.0005

Data Index: 58108 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0251. Min Act: -0.0005

Data Index: 255144 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0272. Min Act: -0.0005

Data Index: 740913 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1154320 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0237. Min Act: -0.0005

Data Index: 47438 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0248. Min Act: -0.0005

Data Index: 31586 (C4 (Web Text))

Max Activating Token Index: 336