Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1625274 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.9414. Min Act: -0.0000

Data Index: 692717 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.9461. Min Act: -0.0000

Data Index: 725994 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7224. Min Act: -0.0000

Data Index: 842388 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1144098 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7860. Min Act: -0.0000

Data Index: 327405 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1873616 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7925. Min Act: -0.0000

Data Index: 826117 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.8869. Min Act: -0.0000

Data Index: 44776 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7398. Min Act: -0.0000

Data Index: 89835 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7355. Min Act: -0.0000

Data Index: 242206 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1609077 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7507. Min Act: -0.0000

Data Index: 740990 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1079881 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.5314. Min Act: -0.0000

Data Index: 706700 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.9085. Min Act: -0.0000

Data Index: 779584 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1628901 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1150650 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1255571 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.5199. Min Act: -0.0000

Data Index: 295446 (The Pile)

Max Activating Token Index: 91