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

Dataset: The Pile

Neuron 2168 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: 1.7981. Min Range: -1.7981

Max Act: 1.7532. Min Act: -0.0000

Data Index: 353295 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7628. Min Act: -0.0000

Data Index: 707219 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7574. Min Act: -0.0000

Data Index: 1345285 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6586. Min Act: -0.0000

Data Index: 625056 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7727. Min Act: -0.0000

Data Index: 194318 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7404. Min Act: -0.0000

Data Index: 245607 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7253. Min Act: -0.0000

Data Index: 233403 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1677616 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1325597 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6490. Min Act: -0.0000

Data Index: 477527 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.4950. Min Act: -0.0000

Data Index: 295358 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6314. Min Act: -0.0000

Data Index: 284241 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7125. Min Act: -0.0000

Data Index: 1779855 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6365. Min Act: -0.0000

Data Index: 243341 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7981. Min Act: -0.0000

Data Index: 247366 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1517338 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6153. Min Act: -0.0000

Data Index: 846629 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6104. Min Act: -0.0000

Data Index: 557648 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6021. Min Act: -0.0000

Data Index: 1112008 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.6832. Min Act: -0.0000

Data Index: 1348214 (The Pile)

Max Activating Token Index: 487