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

Dataset: The Pile

Neuron 1458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1848457 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1734647 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9191. Min Act: -0.0000

Data Index: 637353 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8910. Min Act: -0.0000

Data Index: 494386 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9203. Min Act: 0.0000

Data Index: 1327462 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8557. Min Act: 0.0000

Data Index: 83436 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8541. Min Act: -0.0000

Data Index: 915744 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1542481 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1419908 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9300. Min Act: -0.0000

Data Index: 220519 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1894547 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7540. Min Act: -0.0000

Data Index: 279301 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1122365 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1510277 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1319231 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7583. Min Act: 0.0000

Data Index: 611169 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7603. Min Act: 0.0000

Data Index: 803662 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7571. Min Act: -0.0000

Data Index: 81000 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1678502 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7465. Min Act: -0.0000

Data Index: 246679 (The Pile)

Max Activating Token Index: 651