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

Dataset: The Pile

Neuron 3830 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: 1.7359. Min Range: -1.7359

Max Act: 1.4330. Min Act: -0.0000

Data Index: 1728500 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.7359. Min Act: -0.0000

Data Index: 596964 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1497514 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1567409 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1459950 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3055. Min Act: -0.0000

Data Index: 1328345 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.4223. Min Act: -0.0000

Data Index: 983537 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.1850. Min Act: -0.0000

Data Index: 699367 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.6417. Min Act: -0.0000

Data Index: 564231 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.2402. Min Act: -0.0000

Data Index: 636986 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1434101 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3572. Min Act: -0.0000

Data Index: 244144 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1591595 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1507185 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.2050. Min Act: -0.0000

Data Index: 174931 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.1814. Min Act: -0.0000

Data Index: 547302 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.3761. Min Act: -0.0000

Data Index: 404390 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.2066. Min Act: -0.0000

Data Index: 566463 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.1368. Min Act: -0.0000

Data Index: 553191 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 1.7359. Min Range: -1.7359

Max Act: 1.0507. Min Act: -0.0000

Data Index: 414050 (The Pile)

Max Activating Token Index: 242