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

Dataset: The Pile

Neuron 27 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: 1.8181. Min Range: -1.8181

Max Act: 1.8181. Min Act: -0.0000

Data Index: 1936261 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.6718. Min Act: -0.0000

Data Index: 53657 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1095278 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1336320 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.3980. Min Act: -0.0000

Data Index: 577598 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1270771 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2982. Min Act: -0.0000

Data Index: 271238 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2461. Min Act: -0.0000

Data Index: 282978 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2783. Min Act: -0.0000

Data Index: 180741 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2713. Min Act: -0.0000

Data Index: 696801 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.3035. Min Act: -0.0000

Data Index: 91760 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2718. Min Act: -0.0000

Data Index: 300393 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2273. Min Act: -0.0000

Data Index: 475755 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2503. Min Act: -0.0000

Data Index: 720166 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1672698 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1115429 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1200317 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1940319 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1174092 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.2042. Min Act: -0.0000

Data Index: 612483 (The Pile)

Max Activating Token Index: 385