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

Dataset: The Pile

Neuron 3197 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1906445 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.5686. Min Act: -0.0000

Data Index: 507528 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.6619. Min Act: -0.0000

Data Index: 236373 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1039966 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1589677 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.0951. Min Act: -0.0000

Data Index: 985236 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.1555. Min Act: -0.0000

Data Index: 1159099 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.1443. Min Act: -0.0000

Data Index: 896135 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.0222. Min Act: -0.0000

Data Index: 746779 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.0030. Min Act: -0.0000

Data Index: 346260 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.9617. Min Act: -0.0000

Data Index: 115648 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1057318 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 1.6619. Min Range: -1.6619

Max Act: 1.0068. Min Act: -0.0000

Data Index: 54582 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1960515 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.9514. Min Act: -0.0000

Data Index: 48804 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1540216 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1305146 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1985317 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1702913 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 1.6619. Min Range: -1.6619

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 931