Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1449 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1244326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0340. Min Act: -0.0002

Data Index: 954517 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0321. Min Act: -0.0002

Data Index: 320506 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0318. Min Act: -0.0001

Data Index: 136652 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0308. Min Act: -0.0002

Data Index: 363531 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0317. Min Act: -0.0001

Data Index: 782924 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0297. Min Act: -0.0002

Data Index: 342412 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0307. Min Act: -0.0001

Data Index: 535719 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1416933 (Python Code)

Max Activating Token Index: 874

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0293. Min Act: -0.0002

Data Index: 314082 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1097762 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1148019 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1590620 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1616134 (Python Code)

Max Activating Token Index: 760

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0303. Min Act: -0.0001

Data Index: 996877 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0265. Min Act: -0.0002

Data Index: 806621 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0295. Min Act: -0.0001

Data Index: 237194 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1032532 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0312. Min Act: -0.0001

Data Index: 832447 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1175653 (C4 (Web Text))

Max Activating Token Index: 644