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

Dataset: The Pile

Neuron 3266 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: 0.8445. Min Range: -0.8445

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1926283 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: 0.0000

Data Index: 377458 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1907774 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7405. Min Act: -0.0000

Data Index: 202977 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7261. Min Act: -0.0000

Data Index: 993380 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7145. Min Act: -0.0000

Data Index: 708353 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7055. Min Act: -0.0000

Data Index: 268542 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1542404 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6518. Min Act: -0.0000

Data Index: 772694 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6980. Min Act: -0.0000

Data Index: 70047 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7481. Min Act: -0.0000

Data Index: 677567 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7158. Min Act: -0.0000

Data Index: 616876 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1681435 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1797412 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1221636 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1522264 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1421595 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6829. Min Act: -0.0000

Data Index: 159416 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6426. Min Act: -0.0000

Data Index: 109338 (The Pile)

Max Activating Token Index: 324