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

Dataset: The Pile

Neuron 3677 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: 1.1940. Min Range: -1.1940

Max Act: 1.1940. Min Act: -0.0000

Data Index: 949443 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1342930 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9583. Min Act: -0.0000

Data Index: 7944 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1920791 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1410757 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8120. Min Act: -0.0000

Data Index: 781814 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7452. Min Act: -0.0000

Data Index: 142747 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1062587 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6166. Min Act: -0.0000

Data Index: 178250 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7326. Min Act: -0.0000

Data Index: 58456 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6442. Min Act: -0.0000

Data Index: 276949 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7027. Min Act: -0.0000

Data Index: 640740 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7193. Min Act: -0.0000

Data Index: 900226 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1077869 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1205079 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6804. Min Act: -0.0000

Data Index: 617316 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6733. Min Act: -0.0000

Data Index: 556449 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6561. Min Act: -0.0000

Data Index: 863316 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1186000 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.5714. Min Act: -0.0000

Data Index: 9068 (The Pile)

Max Activating Token Index: 888