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

Dataset: The Pile

Neuron 1220 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: 0.2597. Min Range: -0.2597

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1286741 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1367403 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1375830 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1190867 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1773465 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1688336 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1921567 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1993. Min Act: -0.0000

Data Index: 902391 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1957. Min Act: -0.0000

Data Index: 119802 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2059. Min Act: -0.0000

Data Index: 92496 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2031. Min Act: -0.0000

Data Index: 144751 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1108739 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1956. Min Act: -0.0000

Data Index: 89417 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1683802 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2025. Min Act: -0.0000

Data Index: 679071 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1742900 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1758. Min Act: -0.0000

Data Index: 346351 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1723410 (The Pile)

Max Activating Token Index: 65

Text #18

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1884. Min Act: -0.0000

Data Index: 319951 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1908. Min Act: -0.0000

Data Index: 417150 (The Pile)

Max Activating Token Index: 920