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

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

Neuron 5329 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1277. Min Range: -8.1277

Max Act: 8.1277. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 8.1277. Min Range: -8.1277

Max Act: 7.6086. Min Act: -0.0000

Data Index: 653938 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.9226. Min Act: -0.0000

Data Index: 665462 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.1739. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.4464. Min Act: -0.0000

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.8008. Min Act: -0.0000

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.5653. Min Act: -0.0000

Data Index: 873351 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.7443. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 8.1277. Min Range: -8.1277

Max Act: 6.1115. Min Act: -0.0000

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 8.1277. Min Range: -8.1277

Max Act: 5.3704. Min Act: -0.0000

Data Index: 275260 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 8.1277. Min Range: -8.1277

Max Act: 5.9013. Min Act: -0.0000

Data Index: 901532 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 8.1277. Min Range: -8.1277

Max Act: 4.8802. Min Act: -0.0000

Data Index: 1016408 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 8.1277. Min Range: -8.1277

Max Act: 4.9278. Min Act: -0.0000

Data Index: 583112 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 8.1277. Min Range: -8.1277

Max Act: 5.7620. Min Act: -0.0000

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 8.1277. Min Range: -8.1277

Max Act: 3.7029. Min Act: -0.0000

Data Index: 508691 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 8.1277. Min Range: -8.1277

Max Act: 3.8617. Min Act: -0.0000

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 8.1277. Min Range: -8.1277

Max Act: 4.0238. Min Act: -0.0000

Data Index: 1303537 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 8.1277. Min Range: -8.1277

Max Act: 3.6521. Min Act: -0.0000

Data Index: 623474 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 8.1277. Min Range: -8.1277

Max Act: 4.1172. Min Act: -0.0000

Data Index: 915442 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 8.1277. Min Range: -8.1277

Max Act: 4.1743. Min Act: -0.0000

Data Index: 1429600 (Python Code)

Max Activating Token Index: 991