Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4023 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.7030. Min Act: -0.0000

Data Index: 772608 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6499. Min Act: -0.0000

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6858. Min Act: -0.0000

Data Index: 816997 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5268. Min Act: -0.0000

Data Index: 25517 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1016671 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6124. Min Act: -0.0000

Data Index: 33634 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6092. Min Act: -0.0000

Data Index: 881078 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1344675 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5725. Min Act: -0.0000

Data Index: 475219 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5704. Min Act: -0.0000

Data Index: 849261 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6039. Min Act: -0.0000

Data Index: 820015 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6473. Min Act: -0.0000

Data Index: 168696 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5969. Min Act: -0.0000

Data Index: 485412 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5742. Min Act: -0.0000

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5635. Min Act: -0.0000

Data Index: 683965 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5651. Min Act: -0.0000

Data Index: 758669 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5655. Min Act: -0.0000

Data Index: 902742 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5631. Min Act: -0.0000

Data Index: 774782 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5560. Min Act: -0.0000

Data Index: 602695 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1329222 (C4 (Web Text))

Max Activating Token Index: 226