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

Dataset: The Pile

Neuron 3011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1448558 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.4268. Min Act: -0.0001

Data Index: 785040 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3413. Min Act: -0.0000

Data Index: 400023 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1898671 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3417. Min Act: -0.0000

Data Index: 971902 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1298843 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3191. Min Act: -0.0000

Data Index: 546342 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1771701 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1834159 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1073855 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1932366 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1781299 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3103. Min Act: -0.0000

Data Index: 256917 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1298422 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3159. Min Act: -0.0000

Data Index: 473345 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3280. Min Act: -0.0000

Data Index: 846030 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3077. Min Act: -0.0000

Data Index: 932881 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.2613. Min Act: -0.0000

Data Index: 473996 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.2802. Min Act: -0.0000

Data Index: 769583 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1917492 (The Pile)

Max Activating Token Index: 121