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

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

Neuron 3523 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: 1.8683. Min Range: -1.8683

Max Act: 1.8683. Min Act: -0.0000

Data Index: 5433 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.3235. Min Act: -0.0000

Data Index: 708649 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.3013. Min Act: 0.0000

Data Index: 566176 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1322601 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.3412. Min Act: -0.0000

Data Index: 520958 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.2749. Min Act: 0.0000

Data Index: 719105 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1556795 (Python Code)

Max Activating Token Index: 923

Text #7

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.2342. Min Act: -0.0000

Data Index: 514883 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1558277 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.2296. Min Act: 0.0000

Data Index: 202968 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.1331. Min Act: 0.0000

Data Index: 1019739 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1133531 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.2155. Min Act: -0.0000

Data Index: 33021 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.0652. Min Act: -0.0000

Data Index: 44342 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.1220. Min Act: -0.0000

Data Index: 200070 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.1097. Min Act: -0.0000

Data Index: 633372 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.0967. Min Act: -0.0000

Data Index: 913285 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.0870. Min Act: -0.0000

Data Index: 674530 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1229480 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 1.8683. Min Range: -1.8683

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1012400 (C4 (Web Text))

Max Activating Token Index: 860