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

Dataset: The Pile

Neuron 3836 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: 1.8224. Min Range: -1.8224

Max Act: 1.8224. Min Act: -0.0000

Data Index: 919699 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1098824 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6059. Min Act: -0.0000

Data Index: 911123 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.7727. Min Act: -0.0000

Data Index: 1534981 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.5744. Min Act: -0.0000

Data Index: 291051 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6355. Min Act: -0.0000

Data Index: 1863105 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1747696 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4469. Min Act: -0.0000

Data Index: 130754 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3445. Min Act: -0.0000

Data Index: 98956 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.5434. Min Act: -0.0000

Data Index: 596111 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1603593 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1186953 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1555506 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1304908 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3247. Min Act: -0.0000

Data Index: 203342 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1399349 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1989659 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.1322. Min Act: -0.0000

Data Index: 359093 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1610752 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1340727 (The Pile)

Max Activating Token Index: 281