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

Dataset: The Pile

Neuron 1619 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: 0.6820. Min Range: -0.6820

Max Act: 0.6820. Min Act: -0.0000

Data Index: 330581 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1340884 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4958. Min Act: -0.0000

Data Index: 465244 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4687. Min Act: -0.0000

Data Index: 454870 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5211. Min Act: -0.0000

Data Index: 463480 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4651. Min Act: -0.0000

Data Index: 779833 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4727. Min Act: -0.0000

Data Index: 872682 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1556395 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4212. Min Act: -0.0000

Data Index: 221146 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1996771 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4812. Min Act: -0.0000

Data Index: 73347 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1991898 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4338. Min Act: 0.0000

Data Index: 1826975 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1006378 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1206323 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4207. Min Act: 0.0000

Data Index: 1219819 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4108. Min Act: -0.0000

Data Index: 443502 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4302. Min Act: 0.0000

Data Index: 1219331 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4237. Min Act: -0.0000

Data Index: 445733 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3961. Min Act: -0.0000

Data Index: 675816 (The Pile)

Max Activating Token Index: 543