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

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

Neuron 5817 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1279. Min Range: -2.1279

Max Act: 2.1279. Min Act: -0.0001

Data Index: 919748 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.8631. Min Act: -0.0001

Data Index: 101057 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.8191. Min Act: -0.0000

Data Index: 365359 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.3832. Min Act: -0.0000

Data Index: 812647 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.6348. Min Act: -0.0001

Data Index: 766259 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.3466. Min Act: -0.0000

Data Index: 974944 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2444. Min Act: -0.0001

Data Index: 518647 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.3429. Min Act: -0.0001

Data Index: 909059 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2590. Min Act: -0.0000

Data Index: 270883 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1299706 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.1873. Min Act: -0.0000

Data Index: 639667 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2600. Min Act: -0.0000

Data Index: 401949 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.3748. Min Act: -0.0000

Data Index: 548588 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2017. Min Act: -0.0000

Data Index: 449410 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1028121 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.0797. Min Act: -0.0001

Data Index: 177146 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2984. Min Act: -0.0001

Data Index: 88861 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.2005. Min Act: -0.0000

Data Index: 91686 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.1584. Min Act: -0.0000

Data Index: 655061 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.1279. Min Range: -2.1279

Max Act: 1.1725. Min Act: -0.0001

Data Index: 665485 (C4 (Web Text))

Max Activating Token Index: 681