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

Dataset: The Pile

Neuron 3706 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: 0.5406. Min Range: -0.5406

Max Act: 0.5406. Min Act: -0.0000

Data Index: 11556 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1962630 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1582404 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1319156 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.5082. Min Act: 0.0000

Data Index: 195670 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1221247 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1786550 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1639365 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4843. Min Act: -0.0000

Data Index: 205810 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1038666 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1583222 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4405. Min Act: 0.0000

Data Index: 289467 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4606. Min Act: -0.0000

Data Index: 578416 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1576398 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4500. Min Act: 0.0000

Data Index: 1329776 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1836127 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4185. Min Act: -0.0000

Data Index: 782215 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1635668 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1709022 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.5406. Min Range: -0.5406

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1623451 (The Pile)

Max Activating Token Index: 20