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

Dataset: The Pile

Neuron 3318 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: 0.6351. Min Range: -0.6351

Max Act: 0.6351. Min Act: -0.0000

Data Index: 14644 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5848. Min Act: -0.0000

Data Index: 363650 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1746779 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5394. Min Act: -0.0000

Data Index: 760949 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5223. Min Act: -0.0000

Data Index: 748844 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4713. Min Act: -0.0000

Data Index: 441895 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5287. Min Act: -0.0000

Data Index: 733564 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5260. Min Act: -0.0000

Data Index: 409163 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1771317 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1910237 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4852. Min Act: -0.0000

Data Index: 800576 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4967. Min Act: -0.0000

Data Index: 236625 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5487. Min Act: -0.0000

Data Index: 920848 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1533123 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1468719 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1239406 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5012. Min Act: -0.0000

Data Index: 296954 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4859. Min Act: -0.0000

Data Index: 547428 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4982. Min Act: -0.0000

Data Index: 142329 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1070632 (The Pile)

Max Activating Token Index: 669