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

Dataset: The Pile

Neuron 4816 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1115673 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3881. Min Act: -0.0000

Data Index: 365129 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3632. Min Act: -0.0000

Data Index: 118238 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1766069 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3431. Min Act: -0.0000

Data Index: 36814 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3058. Min Act: -0.0000

Data Index: 755020 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3123. Min Act: -0.0000

Data Index: 517449 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1241658 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1286470 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1975429 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2868. Min Act: -0.0000

Data Index: 574175 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2992. Min Act: -0.0000

Data Index: 440507 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2656. Min Act: -0.0000

Data Index: 385544 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1588324 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1880483 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2471. Min Act: -0.0000

Data Index: 512050 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2745. Min Act: -0.0000

Data Index: 707730 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1917668 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2571. Min Act: -0.0000

Data Index: 322060 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1448922 (The Pile)

Max Activating Token Index: 659