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

Dataset: The Pile

Neuron 4290 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: 0.4343. Min Range: -0.4343

Max Act: 0.4343. Min Act: -0.0000

Data Index: 425341 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3757. Min Act: -0.0000

Data Index: 147225 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1326410 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3296. Min Act: -0.0000

Data Index: 720757 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1938958 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1953517 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1982147 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3119. Min Act: -0.0000

Data Index: 831068 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1739166 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3051. Min Act: -0.0000

Data Index: 220004 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2917. Min Act: -0.0000

Data Index: 378456 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1648494 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2766. Min Act: -0.0000

Data Index: 894285 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2758. Min Act: -0.0000

Data Index: 773909 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2675. Min Act: -0.0000

Data Index: 829139 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1650510 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1075346 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2711. Min Act: -0.0000

Data Index: 160107 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2674. Min Act: -0.0000

Data Index: 380536 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2646. Min Act: -0.0000

Data Index: 879079 (The Pile)

Max Activating Token Index: 223