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

Dataset: The Pile

Neuron 2215 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: 1.1982. Min Range: -1.1982

Max Act: 1.1982. Min Act: -0.0000

Data Index: 924901 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1856906 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0998. Min Act: -0.0000

Data Index: 868336 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0807. Min Act: -0.0000

Data Index: 82521 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0565. Min Act: -0.0000

Data Index: 590635 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0089. Min Act: -0.0000

Data Index: 352039 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9638. Min Act: -0.0000

Data Index: 333366 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0013. Min Act: -0.0000

Data Index: 46819 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9968. Min Act: -0.0000

Data Index: 726965 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1641913 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1863263 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9859. Min Act: -0.0000

Data Index: 226704 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8897. Min Act: -0.0000

Data Index: 256061 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9366. Min Act: -0.0000

Data Index: 78417 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1837489 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9628. Min Act: -0.0000

Data Index: 749350 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1951480 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9529. Min Act: -0.0000

Data Index: 24207 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9240. Min Act: -0.0000

Data Index: 952402 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1286625 (The Pile)

Max Activating Token Index: 373