Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3496. Min Act: -0.0000

Data Index: 371895 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1249405 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3132. Min Act: -0.0000

Data Index: 735850 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2538. Min Act: -0.0000

Data Index: 236634 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2579. Min Act: -0.0000

Data Index: 385949 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2321. Min Act: -0.0000

Data Index: 925068 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1082128 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2142. Min Act: -0.0000

Data Index: 880334 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2261. Min Act: -0.0000

Data Index: 352196 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1204992 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1188162 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2155. Min Act: -0.0000

Data Index: 76296 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1333019 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2174. Min Act: -0.0000

Data Index: 212762 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2310. Min Act: -0.0000

Data Index: 397960 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2014. Min Act: -0.0000

Data Index: 540692 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1190436 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2025. Min Act: -0.0000

Data Index: 939711 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2359. Min Act: -0.0000

Data Index: 238392 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2165. Min Act: -0.0000

Data Index: 925998 (C4 (Web Text))

Max Activating Token Index: 502