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

Dataset: The Pile

Neuron 53 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: 0.9964. Min Range: -0.9964

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1733459 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9466. Min Act: -0.0000

Data Index: 1920064 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1681566 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9964. Min Act: -0.0000

Data Index: 475479 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1218097 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8578. Min Act: -0.0000

Data Index: 543633 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1318225 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8606. Min Act: -0.0000

Data Index: 98031 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1870018 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1447975 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1262614 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1966591 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9195. Min Act: -0.0000

Data Index: 92286 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1359835 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1121240 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8244. Min Act: -0.0000

Data Index: 733016 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8379. Min Act: -0.0000

Data Index: 627541 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1074493 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8630. Min Act: -0.0000

Data Index: 910042 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1905818 (The Pile)

Max Activating Token Index: 814