Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0521. Min Act: -0.0002

Data Index: 835107 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0003

Data Index: 28536 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1340134 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0510. Min Act: -0.0002

Data Index: 177701 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1282209 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0490. Min Act: -0.0002

Data Index: 940343 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0480. Min Act: -0.0003

Data Index: 28949 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0484. Min Act: -0.0003

Data Index: 898967 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0475. Min Act: -0.0003

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0477. Min Act: -0.0003

Data Index: 28496 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1268610 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0457. Min Act: -0.0002

Data Index: 339683 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1223313 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1256836 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0453. Min Act: -0.0003

Data Index: 964125 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1295864 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0441. Min Act: -0.0003

Data Index: 197204 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0431. Min Act: -0.0002

Data Index: 261890 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0442. Min Act: -0.0003

Data Index: 194972 (C4 (Web Text))

Max Activating Token Index: 55