Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 12.0044. Min Range: -12.0044

Max Act: 12.0044. Min Act: -0.0000

Data Index: 907508 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 12.0044. Min Range: -12.0044

Max Act: 11.4172. Min Act: -0.0001

Data Index: 1306793 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 12.0044. Min Range: -12.0044

Max Act: 10.7920. Min Act: -0.0001

Data Index: 494488 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 12.0044. Min Range: -12.0044

Max Act: 10.9812. Min Act: -0.0001

Data Index: 133213 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 12.0044. Min Range: -12.0044

Max Act: 10.4112. Min Act: -0.0001

Data Index: 1000793 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 12.0044. Min Range: -12.0044

Max Act: 10.3715. Min Act: -0.0001

Data Index: 1054952 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 12.0044. Min Range: -12.0044

Max Act: 10.3636. Min Act: -0.0000

Data Index: 537630 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 12.0044. Min Range: -12.0044

Max Act: 10.1373. Min Act: -0.0000

Data Index: 266209 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.8785. Min Act: -0.0000

Data Index: 996417 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.8566. Min Act: -0.0000

Data Index: 1194886 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.7140. Min Act: -0.0000

Data Index: 656952 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.2665. Min Act: -0.0000

Data Index: 1137862 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.4608. Min Act: -0.0001

Data Index: 1243521 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.3500. Min Act: -0.0000

Data Index: 861746 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.2428. Min Act: -0.0001

Data Index: 18454 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.3006. Min Act: -0.0001

Data Index: 1178854 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.3724. Min Act: -0.0001

Data Index: 166327 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 12.0044. Min Range: -12.0044

Max Act: 9.4147. Min Act: -0.0000

Data Index: 1029781 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 12.0044. Min Range: -12.0044

Max Act: 8.9320. Min Act: -0.0001

Data Index: 1154881 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 12.0044. Min Range: -12.0044

Max Act: 8.9704. Min Act: -0.0001

Data Index: 218236 (C4 (Web Text))

Max Activating Token Index: 511