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

Dataset: The Pile

Neuron 661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1563924 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8500. Min Act: -0.0000

Data Index: 385482 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1566546 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1241354 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7378. Min Act: -0.0000

Data Index: 857391 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7348. Min Act: -0.0000

Data Index: 51970 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1078108 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7074. Min Act: -0.0000

Data Index: 826093 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7466. Min Act: -0.0000

Data Index: 203674 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6981. Min Act: -0.0000

Data Index: 708853 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7439. Min Act: -0.0000

Data Index: 110320 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7763. Min Act: -0.0000

Data Index: 197435 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6484. Min Act: -0.0000

Data Index: 144332 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6902. Min Act: -0.0000

Data Index: 785883 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1121385 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1254189 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6398. Min Act: -0.0000

Data Index: 670217 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6634. Min Act: -0.0000

Data Index: 975557 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6702. Min Act: -0.0000

Data Index: 207356 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6981. Min Act: -0.0000

Data Index: 847143 (The Pile)

Max Activating Token Index: 792