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

Dataset: The Pile

Neuron 2871 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: 3.0173. Min Range: -3.0173

Max Act: 3.0173. Min Act: -0.0000

Data Index: 293773 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 3.0173. Min Range: -3.0173

Max Act: 2.3093. Min Act: -0.0000

Data Index: 989406 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 3.0173. Min Range: -3.0173

Max Act: 2.0396. Min Act: -0.0000

Data Index: 1978712 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 3.0173. Min Range: -3.0173

Max Act: 2.0025. Min Act: -0.0000

Data Index: 1349080 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 3.0173. Min Range: -3.0173

Max Act: 2.0226. Min Act: -0.0000

Data Index: 494232 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.9780. Min Act: -0.0000

Data Index: 851318 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.9001. Min Act: -0.0000

Data Index: 680288 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.9444. Min Act: -0.0000

Data Index: 1272769 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 3.0173. Min Range: -3.0173

Max Act: 2.0366. Min Act: -0.0000

Data Index: 1962653 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 3.0173. Min Range: -3.0173

Max Act: 2.4046. Min Act: -0.0000

Data Index: 1505294 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.9661. Min Act: -0.0000

Data Index: 1683241 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.9091. Min Act: -0.0000

Data Index: 89571 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1521143 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.6412. Min Act: -0.0000

Data Index: 164209 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.6181. Min Act: -0.0000

Data Index: 1631969 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1453615 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.6454. Min Act: -0.0000

Data Index: 183938 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1255822 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1697883 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 3.0173. Min Range: -3.0173

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1159325 (The Pile)

Max Activating Token Index: 885