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

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

Neuron 4347 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.8989. Min Act: -0.0000

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1863. Min Act: -0.0000

Data Index: 797954 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.7237. Min Act: -0.0000

Data Index: 307417 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0245. Min Act: -0.0000

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.2367. Min Act: -0.0000

Data Index: 1356026 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0390. Min Act: -0.0000

Data Index: 715935 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.8725. Min Act: -0.0000

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.8783. Min Act: -0.0000

Data Index: 1063783 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.4553. Min Act: -0.0000

Data Index: 1319895 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.4999. Min Act: -0.0000

Data Index: 773120 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.4400. Min Act: -0.0000

Data Index: 66395 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.1777. Min Act: -0.0000

Data Index: 88221 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.2414. Min Act: -0.0000

Data Index: 202059 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.3263. Min Act: -0.0000

Data Index: 1314440 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.2353. Min Act: -0.0000

Data Index: 1112228 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1259636 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.1765. Min Act: -0.0000

Data Index: 615989 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.1566. Min Act: -0.0000

Data Index: 821445 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.3929. Min Act: -0.0000

Data Index: 437000 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.1733. Min Act: -0.0000

Data Index: 876019 (C4 (Web Text))

Max Activating Token Index: 1016