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

Dataset: The Pile

Neuron 4086 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: 1.7546. Min Range: -1.7546

Max Act: 1.7546. Min Act: -0.0000

Data Index: 1214312 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4475. Min Act: -0.0000

Data Index: 272121 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1303616 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4347. Min Act: -0.0000

Data Index: 1036448 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1545410 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4212. Min Act: -0.0000

Data Index: 994957 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1491468 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.2623. Min Act: -0.0000

Data Index: 556021 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.1563. Min Act: -0.0000

Data Index: 345441 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1561248 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.2353. Min Act: -0.0000

Data Index: 378578 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.1928. Min Act: -0.0000

Data Index: 147768 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1932485 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.2303. Min Act: -0.0000

Data Index: 492020 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1380967 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.2288. Min Act: -0.0000

Data Index: 575466 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.2341. Min Act: -0.0000

Data Index: 296684 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.1930. Min Act: -0.0000

Data Index: 2652 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.1358. Min Act: -0.0000

Data Index: 124993 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.2156. Min Act: -0.0000

Data Index: 120524 (The Pile)

Max Activating Token Index: 744