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

Dataset: The Pile

Neuron 757 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: 1.8272. Min Range: -1.8272

Max Act: 1.7286. Min Act: -0.0000

Data Index: 522804 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.8272. Min Act: -0.0000

Data Index: 1667782 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.7661. Min Act: -0.0000

Data Index: 1450538 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.6694. Min Act: -0.0000

Data Index: 1122737 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1330343 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1325467 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4991. Min Act: -0.0000

Data Index: 1125241 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5056. Min Act: -0.0000

Data Index: 2093 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5072. Min Act: -0.0000

Data Index: 37984 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1410732 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4962. Min Act: -0.0000

Data Index: 621984 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3499. Min Act: -0.0000

Data Index: 610334 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1776654 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1683600 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4580. Min Act: -0.0000

Data Index: 701169 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1406859 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4096. Min Act: -0.0000

Data Index: 579892 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1636968 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1081382 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4734. Min Act: -0.0000

Data Index: 1845662 (The Pile)

Max Activating Token Index: 718