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

Dataset: The Pile

Neuron 276 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.8546. Min Act: -0.0000

Data Index: 1690664 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1802933 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.8978. Min Act: -0.0000

Data Index: 211502 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.6492. Min Act: -0.0000

Data Index: 211640 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.5826. Min Act: -0.0000

Data Index: 1402624 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1488415 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1874443 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.1316. Min Act: -0.0000

Data Index: 1854439 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1678579 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1811253 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.2560. Min Act: -0.0000

Data Index: 662113 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1244188 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1824089 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.2648. Min Act: -0.0000

Data Index: 69670 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.0442. Min Act: -0.0000

Data Index: 213835 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1641913 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.1726. Min Act: -0.0000

Data Index: 764757 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1723626 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1991525 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 1.8978. Min Range: -1.8978

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1395885 (The Pile)

Max Activating Token Index: 531