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

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

Neuron 2161 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: 3.1701. Min Range: -3.1701

Max Act: 3.1701. Min Act: -0.0000

Data Index: 794970 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.9347. Min Act: -0.0000

Data Index: 530756 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.1843. Min Act: -0.0000

Data Index: 833855 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.6939. Min Act: -0.0000

Data Index: 678942 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.6199. Min Act: -0.0000

Data Index: 813419 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.7534. Min Act: -0.0000

Data Index: 969770 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.7200. Min Act: -0.0000

Data Index: 27742 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.5896. Min Act: -0.0000

Data Index: 163008 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.5779. Min Act: -0.0000

Data Index: 204483 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.5611. Min Act: -0.0000

Data Index: 281409 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.5539. Min Act: -0.0000

Data Index: 1148054 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.2748. Min Act: -0.0000

Data Index: 143440 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.2565. Min Act: -0.0000

Data Index: 964205 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.2306. Min Act: -0.0000

Data Index: 1102455 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.2275. Min Act: -0.0000

Data Index: 828339 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.2870. Min Act: -0.0000

Data Index: 892669 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.2697. Min Act: -0.0000

Data Index: 876152 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.1192. Min Act: -0.0000

Data Index: 430570 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.0637. Min Act: -0.0000

Data Index: 1155793 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1059685 (C4 (Web Text))

Max Activating Token Index: 112