Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2525 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1457. Min Act: -0.0003

Data Index: 428313 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1439. Min Act: -0.0003

Data Index: 212626 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1258. Min Act: -0.0003

Data Index: 413163 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1347. Min Act: -0.0003

Data Index: 284674 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1309. Min Act: -0.0003

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1328. Min Act: -0.0003

Data Index: 1226635 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1169. Min Act: -0.0003

Data Index: 325699 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1197. Min Act: -0.0003

Data Index: 95220 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1377. Min Act: -0.0003

Data Index: 217585 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1190. Min Act: -0.0003

Data Index: 165686 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1177. Min Act: -0.0003

Data Index: 431724 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1171. Min Act: -0.0003

Data Index: 1213087 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1279. Min Act: -0.0003

Data Index: 441157 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1304. Min Act: -0.0003

Data Index: 1290380 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1164. Min Act: -0.0003

Data Index: 887535 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1173. Min Act: -0.0003

Data Index: 26881 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1124. Min Act: -0.0003

Data Index: 32309 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1092. Min Act: -0.0003

Data Index: 769088 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0932. Min Act: -0.0003

Data Index: 1228621 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1084. Min Act: -0.0003

Data Index: 565833 (C4 (Web Text))

Max Activating Token Index: 281