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

Dataset: The Pile

Neuron 1344 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: 3.1425. Min Range: -3.1425

Max Act: 3.1425. Min Act: -0.0000

Data Index: 1503943 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.1397. Min Act: 0.0000

Data Index: 1740335 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0504. Min Act: -0.0000

Data Index: 1005456 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8575. Min Act: -0.0000

Data Index: 781837 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.9069. Min Act: -0.0000

Data Index: 1230438 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.6693. Min Act: -0.0000

Data Index: 1826937 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.3428. Min Act: -0.0000

Data Index: 507259 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.5602. Min Act: -0.0000

Data Index: 1240264 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.6419. Min Act: -0.0000

Data Index: 1293916 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.4924. Min Act: -0.0000

Data Index: 1681530 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.5229. Min Act: -0.0000

Data Index: 679621 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.5318. Min Act: -0.0000

Data Index: 849479 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.4677. Min Act: -0.0000

Data Index: 622782 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.5651. Min Act: -0.0000

Data Index: 1615334 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.5574. Min Act: -0.0000

Data Index: 1490670 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.1421. Min Act: -0.0000

Data Index: 847809 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.3551. Min Act: -0.0000

Data Index: 1758923 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.2687. Min Act: -0.0000

Data Index: 1042511 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.0597. Min Act: -0.0000

Data Index: 427207 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.2633. Min Act: -0.0000

Data Index: 869609 (The Pile)

Max Activating Token Index: 894