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

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

Neuron 5879 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: 0.1527. Min Range: -0.1527

Max Act: 0.1527. Min Act: -0.0002

Data Index: 977309 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1378. Min Act: -0.0002

Data Index: 249180 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1318. Min Act: -0.0002

Data Index: 1006888 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1329. Min Act: -0.0002

Data Index: 80010 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1344541 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1237. Min Act: -0.0002

Data Index: 971627 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1236. Min Act: -0.0002

Data Index: 966034 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1235. Min Act: -0.0002

Data Index: 803007 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1162570 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1173. Min Act: -0.0002

Data Index: 86286 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1199. Min Act: -0.0002

Data Index: 221539 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1142. Min Act: -0.0002

Data Index: 129927 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1210. Min Act: -0.0002

Data Index: 114281 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1124. Min Act: -0.0002

Data Index: 851009 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1189. Min Act: -0.0002

Data Index: 8595 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1151. Min Act: -0.0002

Data Index: 226654 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1137. Min Act: -0.0002

Data Index: 688145 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1180. Min Act: -0.0002

Data Index: 807678 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1131. Min Act: -0.0002

Data Index: 428808 (C4 (Web Text))

Max Activating Token Index: 311