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

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

Neuron 3831 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1557. Min Act: -0.0000

Data Index: 814306 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1319. Min Act: -0.0000

Data Index: 445535 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1306. Min Act: -0.0000

Data Index: 346322 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1309. Min Act: 0.0000

Data Index: 1086162 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1234467 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1447859 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1293. Min Act: -0.0000

Data Index: 381932 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1271. Min Act: -0.0001

Data Index: 206544 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.0916. Min Act: -0.0000

Data Index: 517203 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1180. Min Act: -0.0000

Data Index: 702229 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1146. Min Act: -0.0000

Data Index: 805924 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1141. Min Act: -0.0000

Data Index: 515669 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1119. Min Act: -0.0000

Data Index: 84377 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1170. Min Act: -0.0000

Data Index: 829732 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1190. Min Act: -0.0000

Data Index: 354079 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1090. Min Act: -0.0000

Data Index: 65944 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1033998 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1595189 (Python Code)

Max Activating Token Index: 433

Text #18

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1069. Min Act: -0.0000

Data Index: 586501 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1207136 (C4 (Web Text))

Max Activating Token Index: 259