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

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

Neuron 5028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.9368. Min Act: -0.0000

Data Index: 214099 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.6721. Min Act: -0.0000

Data Index: 981963 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.6235. Min Act: -0.0000

Data Index: 961369 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.7626. Min Act: -0.0000

Data Index: 896682 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1005140 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.3833. Min Act: -0.0000

Data Index: 68382 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.3538. Min Act: -0.0000

Data Index: 704712 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.5356. Min Act: -0.0000

Data Index: 435954 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.4210. Min Act: -0.0000

Data Index: 837976 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.1677. Min Act: -0.0000

Data Index: 59847 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.4813. Min Act: -0.0000

Data Index: 195090 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.3442. Min Act: -0.0000

Data Index: 420503 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1237587 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1350706 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.2549. Min Act: -0.0000

Data Index: 775607 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.2445. Min Act: -0.0000

Data Index: 864765 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1244950 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1217206 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.2223. Min Act: -0.0000

Data Index: 683111 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.2845. Min Act: -0.0000

Data Index: 1036733 (C4 (Web Text))

Max Activating Token Index: 43