Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0001

Data Index: 439987 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1210736 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2748. Min Act: -0.0000

Data Index: 475267 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1183568 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2579. Min Act: -0.0001

Data Index: 300195 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2533. Min Act: -0.0001

Data Index: 432845 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2411. Min Act: -0.0001

Data Index: 726186 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2449. Min Act: -0.0001

Data Index: 707143 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2501. Min Act: -0.0001

Data Index: 34738 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2274. Min Act: -0.0001

Data Index: 598049 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1038866 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2269. Min Act: -0.0001

Data Index: 34510 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1290177 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1117495 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1231347 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2357. Min Act: -0.0001

Data Index: 371684 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1547583 (Python Code)

Max Activating Token Index: 672

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2371. Min Act: -0.0001

Data Index: 657427 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2155. Min Act: -0.0001

Data Index: 400439 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2320. Min Act: -0.0000

Data Index: 349536 (C4 (Web Text))

Max Activating Token Index: 178