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

Dataset: The Pile

Neuron 2639 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: 1.6250. Min Range: -1.6250

Max Act: 1.6250. Min Act: -0.0000

Data Index: 110783 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1841554 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3463. Min Act: -0.0000

Data Index: 872338 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3977. Min Act: -0.0000

Data Index: 201548 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1702285 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2818. Min Act: -0.0000

Data Index: 226956 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1817. Min Act: -0.0000

Data Index: 977310 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1184514 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1761075 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2295. Min Act: -0.0000

Data Index: 685003 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1174603 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2895. Min Act: -0.0000

Data Index: 88673 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1443209 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2874. Min Act: -0.0000

Data Index: 861690 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1948772 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1177. Min Act: -0.0000

Data Index: 702746 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1193310 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1958946 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1186. Min Act: -0.0000

Data Index: 63392 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1786824 (The Pile)

Max Activating Token Index: 326