Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4967 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1241755 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4419. Min Act: -0.0000

Data Index: 204115 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4225. Min Act: -0.0000

Data Index: 96955 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3679. Min Act: -0.0000

Data Index: 150657 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3795. Min Act: -0.0000

Data Index: 257712 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3782. Min Act: -0.0000

Data Index: 352900 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3362. Min Act: -0.0000

Data Index: 598394 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3458. Min Act: -0.0000

Data Index: 625823 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3335. Min Act: -0.0000

Data Index: 267454 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3438. Min Act: -0.0000

Data Index: 821512 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3152. Min Act: -0.0000

Data Index: 87676 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3265. Min Act: -0.0000

Data Index: 249755 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3272. Min Act: -0.0000

Data Index: 456644 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1202582 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3145. Min Act: -0.0000

Data Index: 533057 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3017. Min Act: -0.0000

Data Index: 611795 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3215. Min Act: -0.0000

Data Index: 386132 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.2981. Min Act: -0.0000

Data Index: 928750 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3035. Min Act: -0.0000

Data Index: 985417 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1084810 (C4 (Web Text))

Max Activating Token Index: 842