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

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

Neuron 3578 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3721. Min Range: -5.3721

Max Act: 5.3721. Min Act: -0.0000

Data Index: 891089 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.8252. Min Act: -0.0000

Data Index: 14488 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.7868. Min Act: -0.0000

Data Index: 674499 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.6829. Min Act: -0.0000

Data Index: 1066196 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.3291. Min Act: -0.0000

Data Index: 795547 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.3004. Min Act: -0.0000

Data Index: 71076 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.4216. Min Act: -0.0000

Data Index: 867139 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.4036. Min Act: -0.0000

Data Index: 914233 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.1950. Min Act: -0.0000

Data Index: 860370 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.1222. Min Act: -0.0000

Data Index: 612133 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.0993. Min Act: -0.0000

Data Index: 493391 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.0596. Min Act: -0.0000

Data Index: 1202987 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 5.3721. Min Range: -5.3721

Max Act: 3.8513. Min Act: -0.0000

Data Index: 1059133 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.0116. Min Act: -0.0000

Data Index: 923625 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.0110. Min Act: -0.0000

Data Index: 558890 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.1909. Min Act: -0.0000

Data Index: 714402 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 5.3721. Min Range: -5.3721

Max Act: 3.8547. Min Act: -0.0000

Data Index: 143691 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 5.3721. Min Range: -5.3721

Max Act: 3.9856. Min Act: -0.0000

Data Index: 640237 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 5.3721. Min Range: -5.3721

Max Act: 4.0927. Min Act: -0.0000

Data Index: 705306 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 5.3721. Min Range: -5.3721

Max Act: 3.8050. Min Act: -0.0000

Data Index: 85336 (C4 (Web Text))

Max Activating Token Index: 891