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

Dataset: The Pile

Neuron 2650 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1764689 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2319. Min Act: -0.0000

Data Index: 522807 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1061655 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1685. Min Act: -0.0000

Data Index: 180555 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2195. Min Act: -0.0000

Data Index: 118772 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2064. Min Act: -0.0000

Data Index: 656130 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1735520 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1674. Min Act: -0.0000

Data Index: 469576 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1476924 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1918016 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1917. Min Act: -0.0000

Data Index: 427145 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1361258 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2052. Min Act: -0.0000

Data Index: 620002 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1844. Min Act: -0.0000

Data Index: 332336 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1825. Min Act: -0.0000

Data Index: 375903 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1329723 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1988455 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1677. Min Act: -0.0000

Data Index: 10471 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1858847 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1576. Min Act: -0.0000

Data Index: 316542 (The Pile)

Max Activating Token Index: 219