Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 855 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1946273 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5959. Min Act: -0.0000

Data Index: 270288 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6423. Min Act: -0.0000

Data Index: 136984 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1752703 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5354. Min Act: -0.0000

Data Index: 788475 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1960344 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5336. Min Act: -0.0000

Data Index: 110541 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1390253 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1306602 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5123. Min Act: -0.0000

Data Index: 471376 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1560104 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1996545 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1221414 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1678823 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4904. Min Act: -0.0000

Data Index: 687202 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1054699 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1584864 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1138127 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4107. Min Act: -0.0000

Data Index: 172187 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1895667 (The Pile)

Max Activating Token Index: 135