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

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

Neuron 5179 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: 2.6398. Min Range: -2.6398

Max Act: 2.6398. Min Act: -0.0000

Data Index: 999136 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 2.6398. Min Range: -2.6398

Max Act: 2.5557. Min Act: -0.0000

Data Index: 626380 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.6398. Min Range: -2.6398

Max Act: 2.0829. Min Act: -0.0000

Data Index: 317241 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 2.6398. Min Range: -2.6398

Max Act: 2.4230. Min Act: -0.0000

Data Index: 1034740 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 2.6398. Min Range: -2.6398

Max Act: 2.2566. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.9438. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.9148. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 2.6398. Min Range: -2.6398

Max Act: 2.0192. Min Act: -0.0000

Data Index: 31687 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.9713. Min Act: -0.0000

Data Index: 505956 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.9768. Min Act: -0.0000

Data Index: 870496 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.9156. Min Act: -0.0000

Data Index: 53387 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.9013. Min Act: -0.0000

Data Index: 680703 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1123221 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.8262. Min Act: -0.0000

Data Index: 4249 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.8922. Min Act: -0.0000

Data Index: 492218 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.7221. Min Act: -0.0000

Data Index: 1546489 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1129448 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.4526. Min Act: -0.0000

Data Index: 953271 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.7862. Min Act: -0.0000

Data Index: 963000 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 2.6398. Min Range: -2.6398

Max Act: 1.7860. Min Act: -0.0000

Data Index: 664951 (C4 (Web Text))

Max Activating Token Index: 595