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

Dataset: The Pile

Neuron 3137 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: 1.5042. Min Range: -1.5042

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1896714 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1269119 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1125950 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.3392. Min Act: -0.0000

Data Index: 635113 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1867760 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2996. Min Act: -0.0000

Data Index: 254977 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2575. Min Act: -0.0000

Data Index: 598631 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1771. Min Act: -0.0000

Data Index: 612782 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1335527 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1147352 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2301. Min Act: -0.0000

Data Index: 910418 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1574. Min Act: -0.0000

Data Index: 829804 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1593026 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1060730 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1889. Min Act: -0.0000

Data Index: 600567 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1145709 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1831887 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1866235 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1743. Min Act: -0.0000

Data Index: 481497 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.1699. Min Act: -0.0000

Data Index: 411376 (The Pile)

Max Activating Token Index: 440