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

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

Neuron 945 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: 3.1200. Min Range: -3.1200

Max Act: 3.1200. Min Act: -0.0000

Data Index: 1050912 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.8359. Min Act: -0.0000

Data Index: 623332 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.7207. Min Act: -0.0000

Data Index: 186754 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.8328. Min Act: -0.0000

Data Index: 711645 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.6726. Min Act: -0.0000

Data Index: 502435 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.5393. Min Act: -0.0000

Data Index: 833589 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.5984. Min Act: -0.0000

Data Index: 85253 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.2524. Min Act: -0.0000

Data Index: 13436 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.6600. Min Act: -0.0000

Data Index: 97764 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.3985. Min Act: -0.0000

Data Index: 323846 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.2802. Min Act: -0.0000

Data Index: 6158 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.2959. Min Act: -0.0000

Data Index: 653656 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.3548. Min Act: -0.0000

Data Index: 1339818 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.3246. Min Act: -0.0000

Data Index: 521775 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.4411. Min Act: -0.0000

Data Index: 154797 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.3272. Min Act: -0.0000

Data Index: 414582 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.2909. Min Act: -0.0000

Data Index: 359493 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.1531. Min Act: -0.0000

Data Index: 832272 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 3.1200. Min Range: -3.1200

Max Act: 2.2776. Min Act: -0.0000

Data Index: 1071012 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.1200. Min Range: -3.1200

Max Act: 1.9359. Min Act: -0.0000

Data Index: 1152829 (C4 (Web Text))

Max Activating Token Index: 209