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

Dataset: The Pile

Neuron 1880 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7092. Min Act: -0.0000

Data Index: 1350840 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5873. Min Act: -0.0000

Data Index: 619872 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7474. Min Act: -0.0000

Data Index: 1827216 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7059. Min Act: -0.0000

Data Index: 796050 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.0299. Min Act: -0.0000

Data Index: 754824 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1764849 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.1456. Min Act: -0.0000

Data Index: 1532526 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.0397. Min Act: -0.0000

Data Index: 463744 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.7621. Min Act: -0.0000

Data Index: 1689369 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.9318. Min Act: -0.0000

Data Index: 761157 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.7669. Min Act: -0.0000

Data Index: 1714453 (The Pile)

Max Activating Token Index: 881

Text #11

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.6261. Min Act: -0.0000

Data Index: 1664589 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.7712. Min Act: -0.0000

Data Index: 326807 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.8435. Min Act: -0.0000

Data Index: 153975 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.5628. Min Act: -0.0000

Data Index: 1386008 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.6429. Min Act: -0.0000

Data Index: 14147 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.4829. Min Act: -0.0000

Data Index: 1283782 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.5933. Min Act: -0.0000

Data Index: 453180 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.5276. Min Act: -0.0000

Data Index: 155642 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 3.7474. Min Range: -3.7474

Max Act: 2.3885. Min Act: -0.0000

Data Index: 1073883 (The Pile)

Max Activating Token Index: 348