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

Dataset: The Pile

Neuron 770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1650450 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.1269. Min Act: -0.0000

Data Index: 767659 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1486285 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9634. Min Act: -0.0000

Data Index: 900604 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.0058. Min Act: -0.0000

Data Index: 2308 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9560. Min Act: -0.0000

Data Index: 424211 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1649499 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1158034 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9731. Min Act: -0.0000

Data Index: 974679 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9381. Min Act: -0.0000

Data Index: 492806 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1207230 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9569. Min Act: -0.0000

Data Index: 460430 (The Pile)

Max Activating Token Index: 724

Text #12

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9435. Min Act: -0.0000

Data Index: 208255 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1690093 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1626262 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1319928 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9997. Min Act: -0.0000

Data Index: 1480655 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1707847 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1467613 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9225. Min Act: -0.0000

Data Index: 416493 (The Pile)

Max Activating Token Index: 209