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

Dataset: The Pile

Neuron 4596 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: 1.8958. Min Range: -1.8958

Max Act: 1.8958. Min Act: -0.0000

Data Index: 1715486 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1731578 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.0023. Min Act: -0.0000

Data Index: 401206 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9741. Min Act: -0.0000

Data Index: 440895 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9421. Min Act: -0.0000

Data Index: 605766 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9335. Min Act: -0.0000

Data Index: 886913 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1442341 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9156. Min Act: -0.0000

Data Index: 141570 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1729333 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1323295 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1545262 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1239389 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8532. Min Act: -0.0000

Data Index: 283076 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1517025 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8969. Min Act: -0.0000

Data Index: 902972 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.9003. Min Act: -0.0000

Data Index: 175974 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1814476 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1998670 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.7855. Min Act: -0.0000

Data Index: 942618 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 1.8958. Min Range: -1.8958

Max Act: 0.8767. Min Act: -0.0000

Data Index: 740897 (The Pile)

Max Activating Token Index: 798