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

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

Neuron 3997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.9173. Min Act: -0.0000

Data Index: 771953 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.8116. Min Act: -0.0000

Data Index: 19118 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.5568. Min Act: -0.0000

Data Index: 101422 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.4715. Min Act: -0.0000

Data Index: 964241 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.0931. Min Act: -0.0000

Data Index: 751688 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.2589. Min Act: -0.0000

Data Index: 1316322 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.2447. Min Act: -0.0000

Data Index: 463502 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.2491. Min Act: -0.0000

Data Index: 369613 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.7843. Min Act: -0.0000

Data Index: 874721 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.9565. Min Act: -0.0000

Data Index: 1064789 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 6.9173. Min Range: -6.9173

Max Act: 6.0170. Min Act: -0.0000

Data Index: 1284861 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.1630. Min Act: -0.0000

Data Index: 468506 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.5006. Min Act: -0.0000

Data Index: 403986 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.5594. Min Act: -0.0000

Data Index: 607231 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.3551. Min Act: -0.0000

Data Index: 681755 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.0140. Min Act: -0.0000

Data Index: 762539 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 6.9173. Min Range: -6.9173

Max Act: 4.9621. Min Act: -0.0000

Data Index: 1002199 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 6.9173. Min Range: -6.9173

Max Act: 5.1568. Min Act: -0.0000

Data Index: 967481 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 6.9173. Min Range: -6.9173

Max Act: 4.9749. Min Act: -0.0000

Data Index: 1046230 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 6.9173. Min Range: -6.9173

Max Act: 4.9478. Min Act: -0.0000

Data Index: 1015332 (C4 (Web Text))

Max Activating Token Index: 354