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

Dataset: The Pile

Neuron 3581 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: 3.7954. Min Range: -3.7954

Max Act: 3.4187. Min Act: -0.0000

Data Index: 517386 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.7954. Min Act: -0.0000

Data Index: 1856022 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2997. Min Act: -0.0000

Data Index: 1292526 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4232. Min Act: -0.0000

Data Index: 1562339 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3539. Min Act: -0.0000

Data Index: 1268040 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3413. Min Act: -0.0000

Data Index: 282687 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1398. Min Act: -0.0000

Data Index: 533297 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1063. Min Act: -0.0000

Data Index: 427290 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2322. Min Act: -0.0000

Data Index: 1390175 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1915. Min Act: -0.0000

Data Index: 860240 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3416. Min Act: -0.0000

Data Index: 1618426 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0528. Min Act: -0.0000

Data Index: 422169 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0528. Min Act: -0.0000

Data Index: 1082539 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3127. Min Act: -0.0000

Data Index: 1172673 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1449. Min Act: -0.0000

Data Index: 979267 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2799. Min Act: -0.0000

Data Index: 1120881 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1160. Min Act: -0.0000

Data Index: 204509 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0636. Min Act: -0.0000

Data Index: 1457927 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2267. Min Act: -0.0000

Data Index: 490 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.8609. Min Act: -0.0000

Data Index: 1373742 (The Pile)

Max Activating Token Index: 642