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

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

Neuron 1253 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: 0.3339. Min Range: -0.3339

Max Act: 0.3339. Min Act: -0.0000

Data Index: 596356 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1139236 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1856. Min Act: -0.0000

Data Index: 493336 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1759. Min Act: -0.0000

Data Index: 71628 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1180327 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1426033 (Python Code)

Max Activating Token Index: 1002

Text #10

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1424. Min Act: -0.0000

Data Index: 538971 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1272. Min Act: -0.0000

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1393487 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1375. Min Act: -0.0000

Data Index: 557702 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1193. Min Act: -0.0000

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1192. Min Act: -0.0000

Data Index: 134743 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1428477 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1120222 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1113489 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1021975 (C4 (Web Text))

Max Activating Token Index: 970