Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 1788 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1404263 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1164710 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1545906 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1999887 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1947167 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6587. Min Act: -0.0001

Data Index: 835150 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6714. Min Act: -0.0001

Data Index: 33022 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1195961 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1738451 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6069. Min Act: -0.0001

Data Index: 1512998 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1797281 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1395752 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6161. Min Act: -0.0001

Data Index: 938428 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6132. Min Act: -0.0001

Data Index: 877844 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6345. Min Act: -0.0001

Data Index: 1164215 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6246. Min Act: -0.0001

Data Index: 1772999 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1209649 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6207. Min Act: -0.0000

Data Index: 985668 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1760695 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5684. Min Act: -0.0001

Data Index: 762524 (The Pile)

Max Activating Token Index: 809