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

Dataset: The Pile

Neuron 1033 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: 0.9117. Min Range: -0.9117

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1838412 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6421. Min Act: -0.0000

Data Index: 714786 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6375. Min Act: -0.0000

Data Index: 455264 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1762365 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5539. Min Act: -0.0000

Data Index: 561359 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5748. Min Act: -0.0000

Data Index: 232874 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1665874 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1369421 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1087535 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1774193 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5650. Min Act: -0.0000

Data Index: 772516 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5318. Min Act: -0.0000

Data Index: 423309 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5030. Min Act: -0.0000

Data Index: 391298 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1084380 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5281. Min Act: -0.0000

Data Index: 311810 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5066. Min Act: -0.0000

Data Index: 424909 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1650073 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1937058 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.4483. Min Act: -0.0000

Data Index: 822884 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1043269 (The Pile)

Max Activating Token Index: 224