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

Dataset: The Pile

Neuron 3181 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: 0.9368. Min Range: -0.9368

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1791763 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9131. Min Act: -0.0000

Data Index: 496285 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1854746 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1927582 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1208464 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1712022 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1103663 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1347504 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1152300 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1868626 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6417. Min Act: -0.0000

Data Index: 328080 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8154. Min Act: -0.0000

Data Index: 938881 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1717815 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1057520 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7513. Min Act: -0.0000

Data Index: 284731 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6548. Min Act: -0.0000

Data Index: 904908 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1747930 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1561216 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1422400 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6570. Min Act: -0.0000

Data Index: 2339 (The Pile)

Max Activating Token Index: 568