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

Dataset: The Pile

Neuron 1172 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: 1.0384. Min Range: -1.0384

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1529900 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8939. Min Act: -0.0000

Data Index: 298559 (The Pile)

Max Activating Token Index: 299

Text #2

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1339484 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1766912 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1803518 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1266041 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6845. Min Act: -0.0000

Data Index: 702166 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1638087 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1077243 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1296594 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6283. Min Act: -0.0000

Data Index: 183185 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1362643 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6412. Min Act: -0.0000

Data Index: 106802 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6119. Min Act: -0.0000

Data Index: 643550 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6002. Min Act: -0.0000

Data Index: 910931 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6009. Min Act: -0.0000

Data Index: 169610 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1782521 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.5163. Min Act: -0.0000

Data Index: 629435 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1774964 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.5679. Min Act: -0.0000

Data Index: 470742 (The Pile)

Max Activating Token Index: 521