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

Dataset: The Pile

Neuron 1352 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: 0.8858. Min Range: -0.8858

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1914820 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7447. Min Act: -0.0000

Data Index: 856665 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1180503 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1282326 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.7590. Min Act: -0.0000

Data Index: 718322 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1055454 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6164. Min Act: -0.0000

Data Index: 640067 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6106. Min Act: -0.0000

Data Index: 347312 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6822. Min Act: -0.0000

Data Index: 326245 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6758. Min Act: -0.0000

Data Index: 131772 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1754503 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4667. Min Act: -0.0000

Data Index: 667348 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5155. Min Act: -0.0000

Data Index: 123590 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1913213 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5026. Min Act: -0.0000

Data Index: 8027 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4221. Min Act: -0.0000

Data Index: 144578 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4706. Min Act: -0.0000

Data Index: 103058 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5291. Min Act: -0.0000

Data Index: 219617 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1002662 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1859693 (The Pile)

Max Activating Token Index: 142