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

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

Neuron 3964 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: 1.7652. Min Range: -1.7652

Max Act: 1.7652. Min Act: -0.0000

Data Index: 334595 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.7260. Min Act: -0.0000

Data Index: 985855 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.7147. Min Act: 0.0000

Data Index: 805714 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.5548. Min Act: -0.0000

Data Index: 1121960 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.3722. Min Act: 0.0000

Data Index: 321039 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.5830. Min Act: -0.0000

Data Index: 64481 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.6778. Min Act: -0.0000

Data Index: 28849 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.6570. Min Act: -0.0000

Data Index: 1284350 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1092734 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.5996. Min Act: -0.0000

Data Index: 950078 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.3459. Min Act: -0.0000

Data Index: 410027 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.3996. Min Act: -0.0000

Data Index: 165232 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.4563. Min Act: -0.0000

Data Index: 68931 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.5209. Min Act: -0.0000

Data Index: 172296 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.1739. Min Act: -0.0000

Data Index: 121499 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1224601 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.5648. Min Act: -0.0000

Data Index: 933812 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.3544. Min Act: -0.0000

Data Index: 749033 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.3411. Min Act: -0.0000

Data Index: 116030 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.7652. Min Range: -1.7652

Max Act: 1.1946. Min Act: -0.0000

Data Index: 831963 (C4 (Web Text))

Max Activating Token Index: 374