Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3265 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1830913 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4048. Min Act: -0.0000

Data Index: 22226 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3820. Min Act: -0.0000

Data Index: 641415 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1081578 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3644. Min Act: 0.0000

Data Index: 494726 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3608. Min Act: 0.0000

Data Index: 581540 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3609. Min Act: -0.0000

Data Index: 711502 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1500175 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3584. Min Act: -0.0000

Data Index: 580911 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1960877 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1487256 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3563. Min Act: -0.0000

Data Index: 664225 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1661165 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3384. Min Act: 0.0000

Data Index: 1110904 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3276. Min Act: -0.0000

Data Index: 788462 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3291. Min Act: -0.0000

Data Index: 698418 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3211. Min Act: -0.0000

Data Index: 245404 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1358250 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1610028 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3313. Min Act: 0.0000

Data Index: 1295395 (The Pile)

Max Activating Token Index: 502