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

Dataset: The Pile

Neuron 4029 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1514735 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3669. Min Act: -0.0000

Data Index: 12949 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1185119 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3770. Min Act: -0.0000

Data Index: 193692 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3681. Min Act: -0.0000

Data Index: 950310 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1329594 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1939388 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3628. Min Act: -0.0000

Data Index: 483057 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3467. Min Act: -0.0000

Data Index: 861073 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3178. Min Act: -0.0000

Data Index: 875909 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3361. Min Act: -0.0000

Data Index: 168717 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1895827 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1606668 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1823367 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1064962 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3051. Min Act: -0.0000

Data Index: 373550 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1332336 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3002. Min Act: -0.0000

Data Index: 940576 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3055. Min Act: -0.0000

Data Index: 414977 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1479996 (The Pile)

Max Activating Token Index: 998