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

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

Neuron 2227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1907. Min Act: -0.0001

Data Index: 755836 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1722. Min Act: -0.0001

Data Index: 353148 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1593. Min Act: -0.0001

Data Index: 330916 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1380. Min Act: -0.0001

Data Index: 77976 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1389. Min Act: -0.0001

Data Index: 220678 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1143271 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1363. Min Act: -0.0001

Data Index: 337963 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1349. Min Act: -0.0001

Data Index: 927926 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1287. Min Act: -0.0001

Data Index: 430504 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1274. Min Act: -0.0001

Data Index: 596515 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1236. Min Act: -0.0001

Data Index: 114041 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1266. Min Act: -0.0001

Data Index: 506284 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1279730 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1214. Min Act: -0.0001

Data Index: 303439 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1202280 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1259859 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1180. Min Act: -0.0001

Data Index: 476838 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1175. Min Act: -0.0001

Data Index: 254033 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1239333 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1140. Min Act: -0.0001

Data Index: 109017 (C4 (Web Text))

Max Activating Token Index: 38