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

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

Neuron 2093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1177. Min Range: -1.1177

Max Act: 1.1177. Min Act: -0.0000

Data Index: 924432 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.1177. Min Range: -1.1177

Max Act: 1.0526. Min Act: -0.0001

Data Index: 540624 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.1177. Min Range: -1.1177

Max Act: 1.0932. Min Act: -0.0001

Data Index: 100999 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 1.1177. Min Range: -1.1177

Max Act: 1.0787. Min Act: -0.0000

Data Index: 857178 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.1177. Min Range: -1.1177

Max Act: 1.0045. Min Act: -0.0001

Data Index: 1314100 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9923. Min Act: -0.0000

Data Index: 461569 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9860. Min Act: -0.0000

Data Index: 462857 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9568. Min Act: -0.0001

Data Index: 330267 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9723. Min Act: -0.0000

Data Index: 208660 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9429. Min Act: -0.0001

Data Index: 246319 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1209443 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9657. Min Act: -0.0001

Data Index: 130233 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9097. Min Act: -0.0001

Data Index: 735626 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9323. Min Act: -0.0000

Data Index: 609422 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9159. Min Act: -0.0001

Data Index: 477037 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9288. Min Act: -0.0000

Data Index: 480791 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9229. Min Act: -0.0000

Data Index: 474733 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1251387 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.9109. Min Act: -0.0001

Data Index: 489362 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.8879. Min Act: -0.0000

Data Index: 939553 (C4 (Web Text))

Max Activating Token Index: 924