Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2019 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.5295. Min Act: -0.0003

Data Index: 1249486 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.5033. Min Act: -0.0003

Data Index: 144890 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4735. Min Act: -0.0003

Data Index: 1130156 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4902. Min Act: -0.0003

Data Index: 1262617 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4733. Min Act: -0.0003

Data Index: 945343 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4772. Min Act: -0.0003

Data Index: 357274 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4446. Min Act: -0.0003

Data Index: 1119078 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4665. Min Act: -0.0003

Data Index: 1264710 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4625. Min Act: -0.0003

Data Index: 1285929 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4498. Min Act: -0.0003

Data Index: 1259432 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4366. Min Act: -0.0003

Data Index: 1466139 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4526. Min Act: -0.0003

Data Index: 359083 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4365. Min Act: -0.0003

Data Index: 636142 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4384. Min Act: -0.0003

Data Index: 476486 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4392. Min Act: -0.0003

Data Index: 1444428 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4138. Min Act: -0.0003

Data Index: 982554 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3792. Min Act: -0.0003

Data Index: 297996 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4328. Min Act: -0.0003

Data Index: 620851 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4233. Min Act: -0.0003

Data Index: 17861 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3829. Min Act: -0.0003

Data Index: 1509582 (Python Code)

Max Activating Token Index: 355