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

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

Neuron 5304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5154. Min Range: -2.5154

Max Act: 2.5154. Min Act: -0.0000

Data Index: 891280 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 2.5154. Min Range: -2.5154

Max Act: 2.3871. Min Act: -0.0000

Data Index: 743671 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 2.5154. Min Range: -2.5154

Max Act: 2.3333. Min Act: -0.0000

Data Index: 1220159 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 2.5154. Min Range: -2.5154

Max Act: 2.1828. Min Act: -0.0000

Data Index: 940504 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 2.5154. Min Range: -2.5154

Max Act: 2.2857. Min Act: -0.0000

Data Index: 1322484 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.9939. Min Act: -0.0000

Data Index: 268796 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.9575. Min Act: -0.0000

Data Index: 104033 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.8717. Min Act: -0.0000

Data Index: 204492 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1352076 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.9008. Min Act: -0.0000

Data Index: 439186 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.7623. Min Act: -0.0000

Data Index: 493567 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.7411. Min Act: -0.0000

Data Index: 1123701 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.7359. Min Act: -0.0000

Data Index: 297708 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.7055. Min Act: -0.0000

Data Index: 480275 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.6526. Min Act: -0.0000

Data Index: 499748 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.6588. Min Act: -0.0000

Data Index: 87140 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.6531. Min Act: -0.0000

Data Index: 232375 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.7454. Min Act: -0.0000

Data Index: 541669 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.6162. Min Act: -0.0000

Data Index: 889389 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 2.5154. Min Range: -2.5154

Max Act: 1.6220. Min Act: -0.0000

Data Index: 439576 (C4 (Web Text))

Max Activating Token Index: 498