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

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

Neuron 933 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5372. Min Range: -6.5372

Max Act: 6.2278. Min Act: -0.0000

Data Index: 1411445 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 6.5372. Min Range: -6.5372

Max Act: 6.2321. Min Act: -0.0000

Data Index: 221397 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 6.5372. Min Range: -6.5372

Max Act: 6.1967. Min Act: -0.0000

Data Index: 1577724 (Python Code)

Max Activating Token Index: 569

Text #3

Max Range: 6.5372. Min Range: -6.5372

Max Act: 6.5372. Min Act: -0.0000

Data Index: 901101 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.7870. Min Act: -0.0000

Data Index: 1473050 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.7600. Min Act: -0.0000

Data Index: 1012442 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.5119. Min Act: -0.0000

Data Index: 905050 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.2744. Min Act: -0.0000

Data Index: 1225295 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.4471. Min Act: -0.0000

Data Index: 825276 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.4631. Min Act: -0.0000

Data Index: 1230334 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.6079. Min Act: -0.0000

Data Index: 1173124 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.4329. Min Act: -0.0000

Data Index: 411684 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.1570. Min Act: -0.0000

Data Index: 450470 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.4219. Min Act: -0.0000

Data Index: 1221368 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.0874. Min Act: -0.0000

Data Index: 1183942 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.0416. Min Act: -0.0000

Data Index: 385576 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 6.5372. Min Range: -6.5372

Max Act: 4.7971. Min Act: -0.0000

Data Index: 889033 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 6.5372. Min Range: -6.5372

Max Act: 4.7578. Min Act: -0.0000

Data Index: 6691 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 6.5372. Min Range: -6.5372

Max Act: 5.1082. Min Act: -0.0000

Data Index: 1010291 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 6.5372. Min Range: -6.5372

Max Act: 4.6536. Min Act: -0.0000

Data Index: 1288275 (C4 (Web Text))

Max Activating Token Index: 740