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

Dataset: The Pile

Neuron 2610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.8034. Min Act: -0.0000

Data Index: 399500 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.7600. Min Act: -0.0000

Data Index: 1018335 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1650519 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.7680. Min Act: -0.0000

Data Index: 908320 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.5781. Min Act: -0.0000

Data Index: 908964 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3971. Min Act: -0.0000

Data Index: 705486 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.5499. Min Act: -0.0000

Data Index: 71216 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1384845 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4634. Min Act: -0.0000

Data Index: 457078 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2144. Min Act: -0.0000

Data Index: 893608 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.5278. Min Act: -0.0000

Data Index: 484773 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3559. Min Act: -0.0000

Data Index: 234318 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3632. Min Act: -0.0000

Data Index: 884020 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3907. Min Act: -0.0000

Data Index: 364358 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1053279 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3497. Min Act: -0.0000

Data Index: 757538 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1248539 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1065677 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2913. Min Act: -0.0000

Data Index: 478284 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2948. Min Act: -0.0000

Data Index: 1455251 (The Pile)

Max Activating Token Index: 898