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

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

Neuron 4544 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6473. Min Range: -2.6473

Max Act: 2.6473. Min Act: -0.0000

Data Index: 63579 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.6473. Min Range: -2.6473

Max Act: 2.3100. Min Act: -0.0000

Data Index: 987238 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.9666. Min Act: -0.0000

Data Index: 1031759 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 2.6473. Min Range: -2.6473

Max Act: 2.2856. Min Act: -0.0000

Data Index: 575398 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.9978. Min Act: -0.0000

Data Index: 65151 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.9640. Min Act: -0.0000

Data Index: 372783 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.9811. Min Act: -0.0000

Data Index: 350755 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 2.6473. Min Range: -2.6473

Max Act: 2.0181. Min Act: -0.0000

Data Index: 560861 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.8752. Min Act: -0.0000

Data Index: 837973 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.8563. Min Act: -0.0000

Data Index: 565567 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.8501. Min Act: -0.0000

Data Index: 1106989 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.8891. Min Act: -0.0000

Data Index: 1099143 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.7162. Min Act: -0.0000

Data Index: 472475 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.5197. Min Act: -0.0000

Data Index: 1071498 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.5470. Min Act: -0.0000

Data Index: 958464 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.6336. Min Act: -0.0000

Data Index: 663387 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.6182. Min Act: -0.0000

Data Index: 771407 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.6980. Min Act: -0.0000

Data Index: 1313491 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.4691. Min Act: -0.0000

Data Index: 766990 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 2.6473. Min Range: -2.6473

Max Act: 1.5356. Min Act: -0.0000

Data Index: 928123 (C4 (Web Text))

Max Activating Token Index: 903