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

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

Neuron 199 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2814. Min Act: -0.0000

Data Index: 409099 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1249451 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1160330 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2724. Min Act: -0.0000

Data Index: 448304 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2590. Min Act: -0.0000

Data Index: 169490 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2530. Min Act: -0.0000

Data Index: 897894 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2307. Min Act: -0.0000

Data Index: 228404 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1258951 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1352191 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2431. Min Act: -0.0000

Data Index: 288973 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2347. Min Act: -0.0000

Data Index: 890052 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1033530 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2275. Min Act: -0.0000

Data Index: 18263 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2319. Min Act: -0.0000

Data Index: 360087 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2393. Min Act: -0.0000

Data Index: 481574 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2359. Min Act: -0.0000

Data Index: 446132 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2342. Min Act: -0.0000

Data Index: 465966 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1183401 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2396. Min Act: -0.0000

Data Index: 533079 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2305. Min Act: -0.0000

Data Index: 146248 (C4 (Web Text))

Max Activating Token Index: 979