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

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

Neuron 6058 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.9085. Min Act: -0.0000

Data Index: 146136 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.6946. Min Act: -0.0000

Data Index: 843533 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.5876. Min Act: 0.0000

Data Index: 106737 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.4705. Min Act: -0.0000

Data Index: 876489 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.3842. Min Act: 0.0001

Data Index: 1135796 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.3626. Min Act: -0.0000

Data Index: 778785 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.4416. Min Act: -0.0000

Data Index: 65547 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.5020. Min Act: -0.0000

Data Index: 100737 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.3313. Min Act: -0.0000

Data Index: 408438 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1179362 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1761. Min Act: -0.0000

Data Index: 754613 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1377257 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1398. Min Act: 0.0000

Data Index: 1008247 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1332. Min Act: -0.0000

Data Index: 11535 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1315. Min Act: 0.0000

Data Index: 145201 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1190509 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1287035 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1413397 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1391893 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 1.9085. Min Range: -1.9085

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1383364 (Python Code)

Max Activating Token Index: 538