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

Dataset: The Pile

Neuron 3605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8874. Min Act: 0.0000

Data Index: 260061 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 5.0143. Min Range: -5.0143

Max Act: 5.0143. Min Act: -0.0000

Data Index: 663996 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.8932. Min Act: -0.0000

Data Index: 1823323 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.7714. Min Act: 0.0000

Data Index: 156731 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.5251. Min Act: -0.0000

Data Index: 1039575 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.4955. Min Act: -0.0000

Data Index: 1879448 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.6665. Min Act: -0.0000

Data Index: 156425 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.5103. Min Act: -0.0000

Data Index: 1732228 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.3006. Min Act: -0.0000

Data Index: 1942899 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.3162. Min Act: -0.0000

Data Index: 686559 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.3940. Min Act: -0.0000

Data Index: 1257318 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.2868. Min Act: -0.0000

Data Index: 1805248 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 5.0143. Min Range: -5.0143

Max Act: 2.8951. Min Act: -0.0000

Data Index: 1213807 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.3608. Min Act: -0.0000

Data Index: 1829028 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 5.0143. Min Range: -5.0143

Max Act: 3.0329. Min Act: -0.0000

Data Index: 1812122 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 5.0143. Min Range: -5.0143

Max Act: 2.8634. Min Act: -0.0000

Data Index: 1676490 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 5.0143. Min Range: -5.0143

Max Act: 2.6731. Min Act: -0.0000

Data Index: 198269 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 5.0143. Min Range: -5.0143

Max Act: 2.8855. Min Act: -0.0000

Data Index: 417899 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 5.0143. Min Range: -5.0143

Max Act: 2.4553. Min Act: -0.0000

Data Index: 41400 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 5.0143. Min Range: -5.0143

Max Act: 2.8826. Min Act: -0.0000

Data Index: 1038658 (The Pile)

Max Activating Token Index: 399