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

Dataset: The Pile

Neuron 3547 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.2714. Min Range: -3.2714

Max Act: 3.2714. Min Act: -0.0000

Data Index: 277418 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 3.2714. Min Range: -3.2714

Max Act: 3.2389. Min Act: -0.0000

Data Index: 1872099 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 3.2714. Min Range: -3.2714

Max Act: 3.1348. Min Act: -0.0000

Data Index: 124936 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 3.2714. Min Range: -3.2714

Max Act: 3.0237. Min Act: -0.0000

Data Index: 1607650 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.3071. Min Act: -0.0000

Data Index: 1121704 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.6583. Min Act: -0.0000

Data Index: 1384301 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.9117. Min Act: -0.0000

Data Index: 1068335 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.9122. Min Act: -0.0000

Data Index: 1756192 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.9365. Min Act: -0.0000

Data Index: 1972284 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.7185. Min Act: -0.0000

Data Index: 1206740 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.6297. Min Act: -0.0000

Data Index: 1326078 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.8378. Min Act: -0.0000

Data Index: 1367396 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.8312. Min Act: -0.0000

Data Index: 851660 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.6408. Min Act: -0.0000

Data Index: 1072439 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.4956. Min Act: -0.0000

Data Index: 388366 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.4938. Min Act: -0.0000

Data Index: 460462 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.5998. Min Act: -0.0000

Data Index: 1883916 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.3562. Min Act: -0.0000

Data Index: 1921647 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.8791. Min Act: -0.0000

Data Index: 796431 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 3.2714. Min Range: -3.2714

Max Act: 2.5787. Min Act: -0.0000

Data Index: 1046340 (The Pile)

Max Activating Token Index: 195