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

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

Neuron 2361 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2461. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2146. Min Act: -0.0000

Data Index: 808236 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1280883 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1558. Min Act: -0.0000

Data Index: 369801 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1106962 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1622. Min Act: -0.0000

Data Index: 282549 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1399. Min Act: -0.0000

Data Index: 40977 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1515. Min Act: -0.0000

Data Index: 999520 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1445. Min Act: -0.0000

Data Index: 55187 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1478. Min Act: -0.0000

Data Index: 667620 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1372095 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1338. Min Act: -0.0000

Data Index: 841238 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1211376 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1264. Min Act: -0.0000

Data Index: 343128 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1256. Min Act: -0.0000

Data Index: 629493 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1207. Min Act: -0.0000

Data Index: 219162 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1591854 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1221452 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1246720 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1205. Min Act: -0.0000

Data Index: 823427 (C4 (Web Text))

Max Activating Token Index: 448