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

Dataset: The Pile

Neuron 2721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1588244 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3053. Min Act: -0.0000

Data Index: 493194 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1954861 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2727. Min Act: -0.0000

Data Index: 464369 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1220257 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2893. Min Act: -0.0000

Data Index: 745298 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2716. Min Act: -0.0000

Data Index: 587473 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2684. Min Act: -0.0000

Data Index: 952256 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2471. Min Act: -0.0000

Data Index: 552683 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1153505 (The Pile)

Max Activating Token Index: 787

Text #10

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2618. Min Act: -0.0000

Data Index: 200042 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1337135 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1195046 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1490684 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2195. Min Act: -0.0000

Data Index: 215133 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1432769 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2362. Min Act: -0.0000

Data Index: 706626 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1193210 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1560182 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2230. Min Act: -0.0000

Data Index: 28432 (The Pile)

Max Activating Token Index: 404