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

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

Neuron 506 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: 1.9744. Min Range: -1.9744

Max Act: 1.9744. Min Act: -0.0001

Data Index: 405875 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.9365. Min Act: -0.0000

Data Index: 544951 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1246165 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.8204. Min Act: -0.0001

Data Index: 32790 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.7335. Min Act: -0.0001

Data Index: 1295468 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.5653. Min Act: -0.0000

Data Index: 219245 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1327823 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4586. Min Act: -0.0001

Data Index: 207425 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4888. Min Act: -0.0000

Data Index: 1239341 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4569. Min Act: -0.0001

Data Index: 535143 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.3157. Min Act: -0.0001

Data Index: 888852 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4481. Min Act: -0.0001

Data Index: 276311 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4370. Min Act: -0.0001

Data Index: 355722 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1182890 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.2435. Min Act: -0.0001

Data Index: 1319783 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.4004. Min Act: -0.0000

Data Index: 988540 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1059762 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.3181. Min Act: -0.0001

Data Index: 24210 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.3110. Min Act: -0.0001

Data Index: 1150992 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.9744. Min Range: -1.9744

Max Act: 1.3714. Min Act: -0.0001

Data Index: 580768 (C4 (Web Text))

Max Activating Token Index: 305