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

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

Neuron 3167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.9554. Min Act: -0.0001

Data Index: 986319 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.9384. Min Act: -0.0001

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.8243. Min Act: -0.0001

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.8001. Min Act: -0.0001

Data Index: 215559 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7346. Min Act: -0.0001

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.8278. Min Act: -0.0001

Data Index: 805454 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7095. Min Act: -0.0001

Data Index: 42020 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7599. Min Act: -0.0001

Data Index: 781495 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6502. Min Act: -0.0000

Data Index: 629402 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7105. Min Act: -0.0000

Data Index: 772927 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7086. Min Act: -0.0000

Data Index: 70552 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7295. Min Act: -0.0001

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6927. Min Act: -0.0001

Data Index: 590917 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6631. Min Act: -0.0000

Data Index: 988820 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6447. Min Act: -0.0001

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6906. Min Act: -0.0001

Data Index: 245028 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1305625 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1316514 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6345. Min Act: -0.0000

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6968. Min Act: -0.0001

Data Index: 400223 (C4 (Web Text))

Max Activating Token Index: 542