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

Dataset: The Pile

Neuron 951 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: 1.2548. Min Range: -1.2548

Max Act: 1.2524. Min Act: -0.0000

Data Index: 341467 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1723281 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.2548. Min Act: -0.0000

Data Index: 122321 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1355613 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0427. Min Act: -0.0000

Data Index: 229474 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0686. Min Act: -0.0000

Data Index: 772911 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0688. Min Act: -0.0000

Data Index: 224916 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0742. Min Act: -0.0000

Data Index: 74189 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1669936 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9901. Min Act: -0.0000

Data Index: 273553 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0451. Min Act: -0.0000

Data Index: 346812 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1529981 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1742829 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0310. Min Act: -0.0000

Data Index: 406629 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0118. Min Act: -0.0000

Data Index: 446601 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1223590 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1741824 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1178083 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9827. Min Act: -0.0000

Data Index: 700729 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9196. Min Act: -0.0000

Data Index: 135214 (The Pile)

Max Activating Token Index: 221