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

Dataset: The Pile

Neuron 3712 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: 0.6436. Min Range: -0.6436

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1823230 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1162545 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1721361 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6163. Min Act: -0.0000

Data Index: 207497 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5508. Min Act: -0.0000

Data Index: 907610 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1896652 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1384837 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5435. Min Act: -0.0000

Data Index: 604902 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5581. Min Act: -0.0000

Data Index: 820784 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5030. Min Act: -0.0000

Data Index: 995535 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1791363 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5490. Min Act: -0.0000

Data Index: 319065 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1610794 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1726891 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1464983 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1060216 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1162962 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1243195 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5095. Min Act: -0.0000

Data Index: 333312 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5157. Min Act: -0.0000

Data Index: 203312 (The Pile)

Max Activating Token Index: 443