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

Dataset: The Pile

Neuron 3678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1628948 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1596747 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.1694. Min Act: -0.0000

Data Index: 107078 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1988143 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.0806. Min Act: -0.0000

Data Index: 918271 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.1231. Min Act: -0.0000

Data Index: 31967 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1465149 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.0512. Min Act: -0.0000

Data Index: 886594 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1855333 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1340891 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.3181. Min Range: -1.3181

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1011303 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9779. Min Act: -0.0000

Data Index: 166862 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9535. Min Act: -0.0000

Data Index: 554013 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9112. Min Act: -0.0000

Data Index: 366626 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1320237 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9138. Min Act: -0.0000

Data Index: 77503 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9229. Min Act: -0.0000

Data Index: 709893 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.8863. Min Act: -0.0000

Data Index: 977711 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9629. Min Act: -0.0000

Data Index: 559793 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 1.3181. Min Range: -1.3181

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1772918 (The Pile)

Max Activating Token Index: 757