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

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

Neuron 3657 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: 0.1672. Min Range: -0.1672

Max Act: 0.1672. Min Act: -0.0002

Data Index: 459432 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1452. Min Act: -0.0002

Data Index: 897555 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1385. Min Act: -0.0002

Data Index: 957727 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1348. Min Act: -0.0002

Data Index: 204922 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1339. Min Act: -0.0002

Data Index: 511157 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1329. Min Act: -0.0002

Data Index: 577856 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1296. Min Act: -0.0002

Data Index: 664021 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1223. Min Act: -0.0002

Data Index: 30579 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1228. Min Act: -0.0002

Data Index: 650347 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1316. Min Act: -0.0002

Data Index: 630459 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1310. Min Act: -0.0002

Data Index: 486306 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1196. Min Act: -0.0002

Data Index: 945690 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1210. Min Act: -0.0002

Data Index: 204289 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1163. Min Act: -0.0002

Data Index: 196014 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1249. Min Act: -0.0002

Data Index: 993265 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1159. Min Act: -0.0002

Data Index: 937183 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1193. Min Act: -0.0002

Data Index: 1220761 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1182. Min Act: -0.0002

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1216. Min Act: -0.0002

Data Index: 422652 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1106765 (C4 (Web Text))

Max Activating Token Index: 568