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

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

Neuron 2446 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: 0.0597. Min Range: -0.0597

Max Act: 0.0581. Min Act: -0.0002

Data Index: 932851 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0002

Data Index: 416853 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0586. Min Act: -0.0002

Data Index: 122350 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1080382 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0556. Min Act: -0.0002

Data Index: 471359 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1158842 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1305508 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1130215 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1308446 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0514. Min Act: -0.0002

Data Index: 138430 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1196906 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0500. Min Act: -0.0002

Data Index: 353026 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0498. Min Act: -0.0002

Data Index: 225404 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1269720 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0492. Min Act: -0.0002

Data Index: 950751 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1341940 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0479. Min Act: -0.0002

Data Index: 271182 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1338093 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1283883 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0476. Min Act: -0.0002

Data Index: 65564 (C4 (Web Text))

Max Activating Token Index: 358