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

Dataset: The Pile

Neuron 539 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1839455 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1556243 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3254. Min Act: -0.0000

Data Index: 864977 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2976. Min Act: -0.0000

Data Index: 282885 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3082. Min Act: -0.0000

Data Index: 457183 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3020. Min Act: 0.0000

Data Index: 1569663 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2706. Min Act: -0.0000

Data Index: 609939 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2715. Min Act: -0.0000

Data Index: 510943 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1247858 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2514. Min Act: -0.0000

Data Index: 63541 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1894582 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1368094 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2503. Min Act: -0.0000

Data Index: 350285 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2244. Min Act: -0.0000

Data Index: 102782 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2362. Min Act: 0.0000

Data Index: 326562 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1133902 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2389. Min Act: -0.0000

Data Index: 855415 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2489. Min Act: -0.0000

Data Index: 845671 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2377. Min Act: -0.0000

Data Index: 293267 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1266003 (The Pile)

Max Activating Token Index: 568