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

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

Neuron 3211 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.3127. Min Act: -0.0000

Data Index: 418598 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1332820 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2769. Min Act: 0.0001

Data Index: 57583 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2770. Min Act: -0.0000

Data Index: 790880 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2881. Min Act: -0.0000

Data Index: 638701 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2482. Min Act: -0.0000

Data Index: 634647 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2268. Min Act: 0.0000

Data Index: 1269732 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2314. Min Act: -0.0000

Data Index: 176382 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2225. Min Act: -0.0000

Data Index: 404007 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2368. Min Act: -0.0000

Data Index: 274430 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2345. Min Act: 0.0001

Data Index: 400631 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2117. Min Act: 0.0000

Data Index: 279597 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2122. Min Act: -0.0001

Data Index: 1310583 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1232826 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1081128 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2173. Min Act: -0.0000

Data Index: 640035 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2046. Min Act: -0.0000

Data Index: 403860 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1086383 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2139. Min Act: 0.0001

Data Index: 362331 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2134. Min Act: -0.0000

Data Index: 556989 (C4 (Web Text))

Max Activating Token Index: 278