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

Dataset: The Pile

Neuron 4591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.6002. Min Act: -0.0000

Data Index: 228762 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.6212. Min Act: -0.0000

Data Index: 258274 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5237. Min Act: -0.0000

Data Index: 385809 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5609. Min Act: -0.0000

Data Index: 319489 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1280869 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5058. Min Act: -0.0000

Data Index: 49832 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1779742 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1693271 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5262. Min Act: -0.0000

Data Index: 65977 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4969. Min Act: -0.0000

Data Index: 231404 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5150. Min Act: -0.0000

Data Index: 899113 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1945920 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4850. Min Act: -0.0000

Data Index: 492028 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1717486 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4850. Min Act: -0.0000

Data Index: 205507 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1452829 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4488. Min Act: -0.0000

Data Index: 919183 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1468652 (The Pile)

Max Activating Token Index: 443