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

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

Neuron 4647 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: 3.6792. Min Range: -3.6792

Max Act: 3.6792. Min Act: -0.0000

Data Index: 733151 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.6792. Min Range: -3.6792

Max Act: 3.6041. Min Act: -0.0000

Data Index: 86614 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 3.6792. Min Range: -3.6792

Max Act: 3.5139. Min Act: -0.0000

Data Index: 232851 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 3.6792. Min Range: -3.6792

Max Act: 3.0040. Min Act: -0.0000

Data Index: 392828 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.9801. Min Act: -0.0000

Data Index: 616885 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 3.6792. Min Range: -3.6792

Max Act: 3.0966. Min Act: -0.0000

Data Index: 931034 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1117487 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.9507. Min Act: -0.0000

Data Index: 427321 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.8710. Min Act: -0.0000

Data Index: 1022727 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.7180. Min Act: -0.0000

Data Index: 831591 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.9608. Min Act: -0.0000

Data Index: 427468 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.9643. Min Act: -0.0000

Data Index: 67709 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.7713. Min Act: -0.0000

Data Index: 1211579 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.8856. Min Act: -0.0000

Data Index: 702851 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.7444. Min Act: -0.0000

Data Index: 403476 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.7459. Min Act: -0.0000

Data Index: 464437 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.6040. Min Act: -0.0000

Data Index: 1350749 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.8679. Min Act: -0.0000

Data Index: 351390 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.8561. Min Act: -0.0000

Data Index: 1355147 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.6792. Min Range: -3.6792

Max Act: 2.8474. Min Act: -0.0000

Data Index: 425436 (C4 (Web Text))

Max Activating Token Index: 930