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

Dataset: The Pile

Neuron 849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1479287 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1339336 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1123306 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1987320 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4797. Min Act: -0.0000

Data Index: 357469 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1708501 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4848. Min Act: -0.0000

Data Index: 126862 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4959. Min Act: -0.0000

Data Index: 242006 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4806. Min Act: -0.0000

Data Index: 316988 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1876410 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5133. Min Act: -0.0000

Data Index: 919541 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4669. Min Act: 0.0000

Data Index: 66086 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4786. Min Act: -0.0000

Data Index: 292509 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4560. Min Act: -0.0000

Data Index: 21326 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1800498 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1969722 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1257889 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1798106 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1347404 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1520896 (The Pile)

Max Activating Token Index: 791