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

Dataset: The Pile

Neuron 2403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1574825 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1709045 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5092. Min Act: -0.0000

Data Index: 115732 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1817740 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1612231 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4727. Min Act: -0.0000

Data Index: 127541 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1245059 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1883283 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4784. Min Act: -0.0000

Data Index: 815150 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1642025 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5055. Min Act: -0.0000

Data Index: 41369 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1052971 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4875. Min Act: -0.0000

Data Index: 481366 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1884952 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1741977 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4679. Min Act: -0.0000

Data Index: 457241 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4833. Min Act: -0.0000

Data Index: 624367 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1087388 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1119030 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1468353 (The Pile)

Max Activating Token Index: 66