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

Dataset: The Pile

Neuron 1350 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.6217. Min Act: -0.0000

Data Index: 530362 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5603. Min Act: -0.0000

Data Index: 448551 (The Pile)

Max Activating Token Index: 546

Text #2

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.6034. Min Act: 0.0003

Data Index: 851614 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1707708 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1713409 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1000735 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1063253 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1221629 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1526498 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4878. Min Act: -0.0000

Data Index: 888557 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4496. Min Act: 0.0001

Data Index: 1776362 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4450. Min Act: 0.0003

Data Index: 932486 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4362. Min Act: -0.0000

Data Index: 778146 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4501. Min Act: -0.0000

Data Index: 315256 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1641798 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4519. Min Act: -0.0000

Data Index: 940956 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4480. Min Act: -0.0000

Data Index: 699653 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1398908 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1015781 (The Pile)

Max Activating Token Index: 840

Text #19

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4169. Min Act: -0.0000

Data Index: 424126 (The Pile)

Max Activating Token Index: 18