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

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

Neuron 2521 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2844. Min Range: -2.2844

Max Act: 2.2844. Min Act: -0.0000

Data Index: 826250 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.2844. Min Range: -2.2844

Max Act: 2.0855. Min Act: -0.0000

Data Index: 161035 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.7124. Min Act: -0.0000

Data Index: 289863 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.6432. Min Act: -0.0000

Data Index: 256190 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.4762. Min Act: -0.0000

Data Index: 172510 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.4633. Min Act: -0.0000

Data Index: 809133 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.4459. Min Act: -0.0000

Data Index: 90365 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.4409. Min Act: 0.0000

Data Index: 230309 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.3004. Min Act: -0.0000

Data Index: 252493 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.3212. Min Act: 0.0000

Data Index: 1035620 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.3372. Min Act: -0.0000

Data Index: 862033 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.3123. Min Act: -0.0000

Data Index: 471447 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.2938. Min Act: -0.0000

Data Index: 933895 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.2135. Min Act: -0.0000

Data Index: 334005 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1327702 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.2900. Min Act: -0.0000

Data Index: 945901 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.2479. Min Act: -0.0000

Data Index: 291694 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1169931 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1098718 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 2.2844. Min Range: -2.2844

Max Act: 1.1914. Min Act: 0.0002

Data Index: 1253514 (C4 (Web Text))

Max Activating Token Index: 475