Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 50 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0002

Data Index: 721468 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0622. Min Act: -0.0002

Data Index: 598701 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0608. Min Act: -0.0002

Data Index: 325729 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0604. Min Act: -0.0002

Data Index: 565123 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1155551 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1009244 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0515. Min Act: -0.0002

Data Index: 921647 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0477. Min Act: -0.0002

Data Index: 465526 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1537238 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1025566 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1258745 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1046675 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0461. Min Act: -0.0002

Data Index: 332814 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0438. Min Act: -0.0002

Data Index: 878988 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0449. Min Act: -0.0002

Data Index: 213979 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0438. Min Act: -0.0002

Data Index: 704215 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0444. Min Act: -0.0002

Data Index: 670132 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0412. Min Act: -0.0002

Data Index: 923321 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0426. Min Act: -0.0002

Data Index: 101148 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1564261 (Python Code)

Max Activating Token Index: 353