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

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

Neuron 2603 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1173416 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.1225. Min Act: -0.0000

Data Index: 919392 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.1936. Min Act: -0.0000

Data Index: 782709 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.0326. Min Act: -0.0000

Data Index: 10201 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.0491. Min Act: -0.0000

Data Index: 170903 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1304830 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.0002. Min Act: -0.0000

Data Index: 176470 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8989. Min Act: -0.0000

Data Index: 524296 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.9598. Min Act: -0.0000

Data Index: 190115 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.3543. Min Range: -1.3543

Max Act: 1.0118. Min Act: -0.0000

Data Index: 17378 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8481. Min Act: -0.0000

Data Index: 943587 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.9205. Min Act: -0.0000

Data Index: 753970 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8889. Min Act: -0.0000

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8338. Min Act: -0.0000

Data Index: 871137 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8710. Min Act: -0.0000

Data Index: 222761 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8089. Min Act: -0.0000

Data Index: 583245 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8535. Min Act: -0.0000

Data Index: 914170 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.9044. Min Act: -0.0000

Data Index: 150328 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.7917. Min Act: -0.0000

Data Index: 618805 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.3543. Min Range: -1.3543

Max Act: 0.8881. Min Act: -0.0000

Data Index: 269378 (C4 (Web Text))

Max Activating Token Index: 833