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

Dataset: The Pile

Neuron 3910 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: 5.0825. Min Range: -5.0825

Max Act: 4.9564. Min Act: -0.0000

Data Index: 1060623 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.3970. Min Act: -0.0000

Data Index: 176007 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 5.0825. Min Range: -5.0825

Max Act: 5.0825. Min Act: -0.0000

Data Index: 690669 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8417. Min Act: -0.0000

Data Index: 67679 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.2269. Min Act: -0.0000

Data Index: 1451394 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.4159. Min Act: -0.0000

Data Index: 1535470 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.1408. Min Act: -0.0000

Data Index: 1749206 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 5.0825. Min Range: -5.0825

Max Act: 3.9737. Min Act: -0.0000

Data Index: 738854 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.2924. Min Act: -0.0000

Data Index: 1022250 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.2924. Min Act: -0.0000

Data Index: 1553777 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.2430. Min Act: -0.0000

Data Index: 190207 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.1028. Min Act: -0.0000

Data Index: 1169337 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.1050. Min Act: -0.0000

Data Index: 1509655 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.1306. Min Act: -0.0000

Data Index: 1757026 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 5.0825. Min Range: -5.0825

Max Act: 3.9756. Min Act: -0.0000

Data Index: 1367231 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.0749. Min Act: -0.0000

Data Index: 362616 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 5.0825. Min Range: -5.0825

Max Act: 3.7779. Min Act: -0.0000

Data Index: 1988897 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 5.0825. Min Range: -5.0825

Max Act: 3.7527. Min Act: -0.0000

Data Index: 1009271 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 5.0825. Min Range: -5.0825

Max Act: 3.8907. Min Act: -0.0000

Data Index: 1058405 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 5.0825. Min Range: -5.0825

Max Act: 3.9009. Min Act: -0.0000

Data Index: 1754810 (The Pile)

Max Activating Token Index: 435