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

Dataset: The Pile

Neuron 1304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1648398 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1422723 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7962. Min Act: -0.0000

Data Index: 130762 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1381482 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1047019 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1888039 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1251342 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1242936 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7512. Min Act: -0.0000

Data Index: 834509 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1719994 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6769. Min Act: -0.0000

Data Index: 736094 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1608601 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1914758 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6453. Min Act: -0.0000

Data Index: 344754 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6506. Min Act: -0.0000

Data Index: 661175 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1940403 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1009196 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6341. Min Act: -0.0000

Data Index: 260096 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1094696 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1121321 (The Pile)

Max Activating Token Index: 531