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

Dataset: The Pile

Neuron 285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1192509 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1546295 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2961. Min Act: -0.0000

Data Index: 719862 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.3224. Min Act: -0.0000

Data Index: 312272 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1647187 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2957. Min Act: -0.0000

Data Index: 405928 (The Pile)

Max Activating Token Index: 809

Text #6

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1169424 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1618142 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1152558 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1359838 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2857. Min Act: -0.0000

Data Index: 976931 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1964. Min Act: -0.0000

Data Index: 204822 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1138691 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1490. Min Act: -0.0000

Data Index: 376548 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1388. Min Act: -0.0000

Data Index: 865762 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1472743 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1731502 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0799. Min Act: -0.0000

Data Index: 669848 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1690. Min Act: -0.0000

Data Index: 580062 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1003105 (The Pile)

Max Activating Token Index: 707