Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9708. Min Act: -0.0000

Data Index: 262714 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8439. Min Act: -0.0000

Data Index: 972793 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8998. Min Act: -0.0000

Data Index: 142121 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 3.0055. Min Range: -3.0055

Max Act: 3.0055. Min Act: -0.0000

Data Index: 598352 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.7253. Min Act: -0.0000

Data Index: 1789479 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.7158. Min Act: -0.0000

Data Index: 728020 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.7205. Min Act: -0.0000

Data Index: 44657 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.6026. Min Act: -0.0000

Data Index: 75258 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.6095. Min Act: -0.0000

Data Index: 178426 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.2145. Min Act: -0.0000

Data Index: 1900773 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.2779. Min Act: -0.0000

Data Index: 1816574 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.0303. Min Act: -0.0000

Data Index: 474297 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.0642. Min Act: -0.0000

Data Index: 1071003 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1633532 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.9439. Min Act: -0.0000

Data Index: 952978 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.9835. Min Act: -0.0000

Data Index: 107858 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.8779. Min Act: -0.0000

Data Index: 501743 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.9340. Min Act: -0.0000

Data Index: 259850 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.8619. Min Act: -0.0000

Data Index: 961056 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 3.0055. Min Range: -3.0055

Max Act: 1.9576. Min Act: -0.0000

Data Index: 1832537 (The Pile)

Max Activating Token Index: 205