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

Dataset: The Pile

Neuron 3795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1965614 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1046639 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1056287 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1704472 (The Pile)

Max Activating Token Index: 328

Text #4

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7892. Min Act: -0.0000

Data Index: 336599 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1703686 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7174. Min Act: -0.0000

Data Index: 568076 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7424. Min Act: -0.0000

Data Index: 375698 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7626. Min Act: -0.0000

Data Index: 470153 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1889244 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6589. Min Act: -0.0000

Data Index: 685042 (The Pile)

Max Activating Token Index: 697

Text #11

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6776. Min Act: -0.0000

Data Index: 146270 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6584. Min Act: -0.0000

Data Index: 242837 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1899344 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1995116 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7232. Min Act: -0.0000

Data Index: 485693 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1949476 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1324127 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7249. Min Act: -0.0000

Data Index: 834696 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7384. Min Act: -0.0000

Data Index: 494846 (The Pile)

Max Activating Token Index: 1004