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

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

Neuron 782 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: 0.6149. Min Range: -0.6149

Max Act: 0.6149. Min Act: -0.0000

Data Index: 604953 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5579. Min Act: 0.0000

Data Index: 1227348 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5546. Min Act: -0.0000

Data Index: 39419 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1316466 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5407. Min Act: -0.0000

Data Index: 542522 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5365. Min Act: 0.0001

Data Index: 415664 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5115. Min Act: -0.0000

Data Index: 435258 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.5262. Min Act: -0.0000

Data Index: 996016 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4944. Min Act: -0.0000

Data Index: 788297 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4925. Min Act: -0.0000

Data Index: 908976 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1073260 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4850. Min Act: -0.0000

Data Index: 168489 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4835. Min Act: -0.0000

Data Index: 250820 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4582. Min Act: -0.0000

Data Index: 256534 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4521. Min Act: -0.0000

Data Index: 750972 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1235281 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1099010 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4457. Min Act: -0.0000

Data Index: 834821 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4763. Min Act: -0.0000

Data Index: 16387 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.6149. Min Range: -0.6149

Max Act: 0.4970. Min Act: -0.0000

Data Index: 329676 (C4 (Web Text))

Max Activating Token Index: 864