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

Dataset: The Pile

Neuron 2676 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: 1.5896. Min Range: -1.5896

Max Act: 1.5896. Min Act: -0.0000

Data Index: 456398 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.4226. Min Act: -0.0000

Data Index: 99196 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1282816 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2998. Min Act: -0.0000

Data Index: 313940 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1104697 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1636833 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9959. Min Act: -0.0000

Data Index: 770197 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1171912 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0031. Min Act: -0.0000

Data Index: 735124 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1851980 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1544887 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1028168 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9959. Min Act: -0.0000

Data Index: 658720 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1294661 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1081887 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1807700 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1204813 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1474131 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1980013 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8735. Min Act: -0.0000

Data Index: 893653 (The Pile)

Max Activating Token Index: 708