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

Dataset: The Pile

Neuron 3865 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: 1.9975. Min Range: -1.9975

Max Act: 1.9975. Min Act: -0.0000

Data Index: 1562322 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.7811. Min Act: -0.0000

Data Index: 716086 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.9212. Min Act: -0.0000

Data Index: 735335 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.5574. Min Act: -0.0000

Data Index: 882092 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.8287. Min Act: -0.0000

Data Index: 486880 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1950165 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.6280. Min Act: -0.0000

Data Index: 410754 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1651493 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.5903. Min Act: -0.0000

Data Index: 963607 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.6893. Min Act: -0.0000

Data Index: 1291615 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.6389. Min Act: -0.0000

Data Index: 121912 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1293364 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.4426. Min Act: -0.0000

Data Index: 807926 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1028365 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.5230. Min Act: -0.0000

Data Index: 667325 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1609502 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.4096. Min Act: -0.0000

Data Index: 215537 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1032388 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.4773. Min Act: -0.0000

Data Index: 84170 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.3874. Min Act: -0.0000

Data Index: 166900 (The Pile)

Max Activating Token Index: 948