Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.8929. Min Act: -0.0000

Data Index: 565768 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.8096. Min Act: -0.0000

Data Index: 908373 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1267932 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.7258. Min Act: -0.0000

Data Index: 902220 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1177886 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1464497 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1694176 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6851. Min Act: -0.0000

Data Index: 311974 (The Pile)

Max Activating Token Index: 671

Text #8

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1265439 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6477. Min Act: -0.0000

Data Index: 860869 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1941411 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6620. Min Act: -0.0000

Data Index: 664286 (The Pile)

Max Activating Token Index: 168

Text #12

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1079503 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1210216 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.7088. Min Act: -0.0000

Data Index: 460758 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6736. Min Act: -0.0000

Data Index: 539384 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1747247 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.5963. Min Act: -0.0000

Data Index: 402947 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6428. Min Act: -0.0000

Data Index: 496048 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1646521 (The Pile)

Max Activating Token Index: 853