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

Dataset: The Pile

Neuron 1986 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: 0.8539. Min Range: -0.8539

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1350983 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1948400 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7577. Min Act: 0.0000

Data Index: 87369 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1224242 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7211. Min Act: -0.0000

Data Index: 672060 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1885873 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7252. Min Act: 0.0000

Data Index: 410898 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6979. Min Act: -0.0000

Data Index: 677627 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1249522 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1618019 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6830. Min Act: -0.0000

Data Index: 34571 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1782820 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6786. Min Act: 0.0000

Data Index: 1612958 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7165. Min Act: -0.0000

Data Index: 342721 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6650. Min Act: -0.0000

Data Index: 296080 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6386. Min Act: -0.0000

Data Index: 82331 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1192554 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1062060 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1077775 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1142347 (The Pile)

Max Activating Token Index: 821