Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2686 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1270223 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1105453 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1350. Min Act: -0.0002

Data Index: 1034436 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1454. Min Act: -0.0001

Data Index: 690148 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1360. Min Act: -0.0002

Data Index: 596666 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1586. Min Act: -0.0001

Data Index: 447345 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1355845 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1234633 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1396. Min Act: -0.0001

Data Index: 571852 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1338. Min Act: -0.0001

Data Index: 195300 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1306. Min Act: -0.0002

Data Index: 929390 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1231268 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1144348 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1229. Min Act: -0.0001

Data Index: 248270 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1209. Min Act: -0.0002

Data Index: 569335 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1228406 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1179726 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1226. Min Act: -0.0002

Data Index: 474550 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1227. Min Act: -0.0001

Data Index: 56439 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1107. Min Act: -0.0002

Data Index: 501263 (C4 (Web Text))

Max Activating Token Index: 595