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

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

Neuron 3545 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9998. Min Act: -0.0002

Data Index: 325272 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9868. Min Act: -0.0002

Data Index: 165551 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9476. Min Act: -0.0002

Data Index: 680103 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8932. Min Act: -0.0002

Data Index: 481329 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8211. Min Act: -0.0002

Data Index: 610515 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8152. Min Act: -0.0002

Data Index: 795674 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8348. Min Act: -0.0002

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7815. Min Act: -0.0002

Data Index: 528575 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7928. Min Act: -0.0002

Data Index: 1274133 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7645. Min Act: -0.0002

Data Index: 620391 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6874. Min Act: -0.0002

Data Index: 906703 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7838. Min Act: -0.0002

Data Index: 1163454 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7817. Min Act: -0.0002

Data Index: 1285159 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7633. Min Act: -0.0002

Data Index: 908170 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7189. Min Act: -0.0002

Data Index: 1054131 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7327. Min Act: -0.0002

Data Index: 765054 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7541. Min Act: -0.0002

Data Index: 417633 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7295. Min Act: -0.0002

Data Index: 587359 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7179. Min Act: -0.0002

Data Index: 722677 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7599. Min Act: -0.0002

Data Index: 280788 (C4 (Web Text))

Max Activating Token Index: 506