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

Dataset: The Pile

Neuron 3029 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: 0.2717. Min Range: -0.2717

Max Act: 0.2717. Min Act: -0.0000

Data Index: 119069 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1818. Min Act: -0.0000

Data Index: 969284 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1699734 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1119732 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1970452 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1214555 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2246. Min Act: -0.0000

Data Index: 829456 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2258. Min Act: -0.0000

Data Index: 872645 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2277. Min Act: -0.0000

Data Index: 864931 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1639243 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1051643 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2274. Min Act: -0.0000

Data Index: 579833 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2023. Min Act: -0.0000

Data Index: 401504 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1856912 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2056. Min Act: -0.0000

Data Index: 741058 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1954609 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1161158 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1904. Min Act: -0.0000

Data Index: 352999 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1235915 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1800. Min Act: -0.0000

Data Index: 141877 (The Pile)

Max Activating Token Index: 535