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

Dataset: The Pile

Neuron 3312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1335997 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7349. Min Act: -0.0000

Data Index: 837752 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7076. Min Act: -0.0000

Data Index: 250865 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1081483 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6860. Min Act: -0.0000

Data Index: 512846 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1450455 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1877745 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.8131. Min Act: -0.0000

Data Index: 871479 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1909277 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6414. Min Act: -0.0000

Data Index: 819389 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5871. Min Act: -0.0000

Data Index: 90602 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1662006 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6131. Min Act: -0.0000

Data Index: 60905 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1583627 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6234. Min Act: -0.0000

Data Index: 457427 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6154. Min Act: -0.0000

Data Index: 785026 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5156. Min Act: -0.0000

Data Index: 686828 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1535761 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1450574 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1516588 (The Pile)

Max Activating Token Index: 501