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

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

Neuron 5501 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: 1.2539. Min Range: -1.2539

Max Act: 1.2539. Min Act: -0.0000

Data Index: 543949 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.8773. Min Act: -0.0000

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1271556 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7635. Min Act: -0.0000

Data Index: 191762 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.8647. Min Act: -0.0000

Data Index: 956613 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1056221 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7686. Min Act: -0.0000

Data Index: 428516 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.8066. Min Act: -0.0000

Data Index: 676042 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1071223 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7867. Min Act: -0.0000

Data Index: 894733 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1252544 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.7087. Min Act: -0.0000

Data Index: 196288 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6653. Min Act: -0.0000

Data Index: 326179 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6642. Min Act: -0.0000

Data Index: 867469 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6896. Min Act: -0.0000

Data Index: 611268 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6528. Min Act: -0.0000

Data Index: 384747 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1020934 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1224837 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6438. Min Act: -0.0000

Data Index: 950759 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.2539. Min Range: -1.2539

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1200041 (C4 (Web Text))

Max Activating Token Index: 662