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

Dataset: The Pile

Neuron 4009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1230792 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.3045. Min Act: -0.0000

Data Index: 175181 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1450349 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2611. Min Act: -0.0000

Data Index: 350303 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2696. Min Act: -0.0000

Data Index: 513956 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1754374 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1020602 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1640911 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1605798 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1897920 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1041623 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2444. Min Act: -0.0000

Data Index: 900717 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2418. Min Act: -0.0000

Data Index: 224203 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2335. Min Act: -0.0000

Data Index: 886661 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2335. Min Act: -0.0000

Data Index: 212323 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1120288 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1446916 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1822106 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2337. Min Act: -0.0000

Data Index: 387061 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2167. Min Act: -0.0000

Data Index: 201970 (The Pile)

Max Activating Token Index: 760