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

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

Neuron 1192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.9721. Min Act: -0.0000

Data Index: 699180 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.7283. Min Act: -0.0000

Data Index: 535883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1158084 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3596. Min Act: -0.0000

Data Index: 336687 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2684. Min Act: -0.0001

Data Index: 148627 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3520. Min Act: -0.0000

Data Index: 830103 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3326. Min Act: -0.0000

Data Index: 651577 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2501. Min Act: -0.0000

Data Index: 756471 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3657. Min Act: -0.0000

Data Index: 566938 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2883. Min Act: -0.0000

Data Index: 793778 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1316729 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.4184. Min Act: -0.0000

Data Index: 52438 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.4031. Min Act: -0.0000

Data Index: 278627 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3655. Min Act: -0.0000

Data Index: 593386 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3200. Min Act: -0.0000

Data Index: 847303 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3144. Min Act: -0.0000

Data Index: 510770 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.3484. Min Act: -0.0000

Data Index: 491495 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2445. Min Act: -0.0000

Data Index: 901076 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2612. Min Act: -0.0000

Data Index: 475703 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.9721. Min Range: -1.9721

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1273744 (C4 (Web Text))

Max Activating Token Index: 615