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

Dataset: The Pile

Neuron 1354 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1340532 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1470551 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1980718 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4436. Min Act: -0.0000

Data Index: 502858 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1178406 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1324092 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1702865 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1061513 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4160. Min Act: -0.0000

Data Index: 400738 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1590212 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1285692 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3544. Min Act: -0.0000

Data Index: 201664 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3981. Min Act: -0.0000

Data Index: 202612 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1430600 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3606. Min Act: -0.0000

Data Index: 422871 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3543. Min Act: -0.0000

Data Index: 618060 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1989240 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1980598 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3727. Min Act: -0.0000

Data Index: 459604 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3519. Min Act: -0.0000

Data Index: 225720 (The Pile)

Max Activating Token Index: 932