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

Dataset: The Pile

Neuron 3759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1846001 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2675. Min Act: -0.0000

Data Index: 139920 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2540. Min Act: -0.0000

Data Index: 813909 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2634. Min Act: -0.0000

Data Index: 133808 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2417. Min Act: -0.0000

Data Index: 841186 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1821904 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2549. Min Act: -0.0000

Data Index: 149982 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1418716 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1166809 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2353. Min Act: -0.0000

Data Index: 745734 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1642485 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2281. Min Act: -0.0000

Data Index: 466674 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2187. Min Act: -0.0000

Data Index: 467316 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1183453 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1280188 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2248. Min Act: -0.0000

Data Index: 105793 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1734876 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2100. Min Act: -0.0000

Data Index: 979792 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2006. Min Act: -0.0000

Data Index: 608919 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2147. Min Act: -0.0000

Data Index: 57313 (The Pile)

Max Activating Token Index: 393