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

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

Neuron 766 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0751. Min Range: -1.0751

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1147327 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.0751. Min Range: -1.0751

Max Act: 1.0003. Min Act: -0.0000

Data Index: 86240 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1178104 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1260885 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8209. Min Act: -0.0000

Data Index: 434173 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8269. Min Act: -0.0000

Data Index: 547670 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1335812 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8244. Min Act: -0.0000

Data Index: 288755 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1061706 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1262597 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1350029 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1059772 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8159. Min Act: -0.0000

Data Index: 454659 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7519. Min Act: -0.0000

Data Index: 821693 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7553. Min Act: -0.0000

Data Index: 213821 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1131682 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7320. Min Act: -0.0000

Data Index: 427273 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7417. Min Act: -0.0000

Data Index: 790659 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1242815 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1137382 (C4 (Web Text))

Max Activating Token Index: 511