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

Dataset: The Pile

Neuron 2572 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.4092. Min Act: -0.0000

Data Index: 655439 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2486. Min Act: -0.0000

Data Index: 792832 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2959. Min Act: -0.0000

Data Index: 63477 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1577867 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1200389 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1156. Min Act: -0.0000

Data Index: 928001 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1192525 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1937779 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1145385 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1823964 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1949575 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1891339 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1568166 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1434. Min Act: -0.0000

Data Index: 29163 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1571944 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1606550 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2763. Min Act: -0.0000

Data Index: 895027 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1719. Min Act: -0.0000

Data Index: 728668 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1175823 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1733116 (The Pile)

Max Activating Token Index: 678