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

Dataset: The Pile

Neuron 2426 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3270. Min Range: -3.3270

Max Act: 3.2474. Min Act: -0.0000

Data Index: 381165 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.9728. Min Act: -0.0000

Data Index: 546625 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.9275. Min Act: -0.0000

Data Index: 1684490 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.6482. Min Act: -0.0000

Data Index: 435062 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.7470. Min Act: -0.0000

Data Index: 1458337 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.8671. Min Act: -0.0000

Data Index: 1324476 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.8520. Min Act: -0.0000

Data Index: 609822 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.5653. Min Act: -0.0000

Data Index: 175607 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 3.3270. Min Range: -3.3270

Max Act: 3.3270. Min Act: -0.0000

Data Index: 200035 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.5194. Min Act: -0.0000

Data Index: 649035 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.6075. Min Act: -0.0000

Data Index: 1979106 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.5198. Min Act: -0.0000

Data Index: 871189 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.2779. Min Act: -0.0000

Data Index: 351107 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.3713. Min Act: -0.0000

Data Index: 372568 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.5086. Min Act: -0.0000

Data Index: 1807929 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.3588. Min Act: -0.0000

Data Index: 186350 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.3016. Min Act: -0.0000

Data Index: 1777098 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.8476. Min Act: -0.0000

Data Index: 1135558 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.4510. Min Act: -0.0000

Data Index: 147363 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 3.3270. Min Range: -3.3270

Max Act: 2.4510. Min Act: -0.0000

Data Index: 479035 (The Pile)

Max Activating Token Index: 987