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

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

Neuron 2626 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: 0.4541. Min Range: -0.4541

Max Act: 0.4541. Min Act: -0.0000

Data Index: 196709 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1144632 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4023. Min Act: -0.0000

Data Index: 98264 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1070190 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3348. Min Act: -0.0000

Data Index: 209433 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1215188 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3254. Min Act: -0.0000

Data Index: 253897 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1228498 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2723. Min Act: -0.0000

Data Index: 475634 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2726. Min Act: -0.0000

Data Index: 890167 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2986. Min Act: -0.0000

Data Index: 127747 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2866. Min Act: -0.0000

Data Index: 356887 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2966. Min Act: -0.0000

Data Index: 836881 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2328. Min Act: -0.0000

Data Index: 899761 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2551. Min Act: -0.0000

Data Index: 794165 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1113714 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2191. Min Act: -0.0000

Data Index: 236912 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2501. Min Act: -0.0000

Data Index: 313468 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2403. Min Act: -0.0000

Data Index: 756763 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1055603 (C4 (Web Text))

Max Activating Token Index: 363