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

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

Neuron 6120 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.3562. Min Act: -0.0000

Data Index: 1250724 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.1703. Min Act: -0.0000

Data Index: 802686 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.1324. Min Act: -0.0000

Data Index: 99125 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.0441. Min Act: -0.0000

Data Index: 128156 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9122. Min Act: -0.0000

Data Index: 281180 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.0150. Min Act: -0.0000

Data Index: 795251 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.0219. Min Act: -0.0000

Data Index: 1239457 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.0125. Min Act: -0.0000

Data Index: 678730 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.1154. Min Act: -0.0000

Data Index: 213225 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9710. Min Act: -0.0000

Data Index: 387834 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9587. Min Act: -0.0000

Data Index: 868823 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9501. Min Act: -0.0000

Data Index: 446216 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9452. Min Act: -0.0000

Data Index: 851751 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.3562. Min Range: -2.3562

Max Act: 2.0383. Min Act: -0.0000

Data Index: 109586 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9604. Min Act: -0.0000

Data Index: 1390603 (Python Code)

Max Activating Token Index: 631

Text #15

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.7379. Min Act: -0.0000

Data Index: 213981 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.9466. Min Act: -0.0000

Data Index: 592931 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.8387. Min Act: -0.0000

Data Index: 1604306 (Python Code)

Max Activating Token Index: 803

Text #18

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.8376. Min Act: -0.0000

Data Index: 96405 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 2.3562. Min Range: -2.3562

Max Act: 1.8259. Min Act: -0.0000

Data Index: 713183 (C4 (Web Text))

Max Activating Token Index: 511