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

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

Neuron 2175 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.5449. Min Act: -0.0000

Data Index: 986424 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1239504 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2930. Min Act: -0.0000

Data Index: 568110 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2813. Min Act: -0.0000

Data Index: 984937 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1331379 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2622. Min Act: -0.0000

Data Index: 129772 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2609. Min Act: -0.0000

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2683. Min Act: -0.0000

Data Index: 342154 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1299933 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2709. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2420. Min Act: -0.0000

Data Index: 520447 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1198459 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2558. Min Act: -0.0000

Data Index: 354945 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2267. Min Act: -0.0000

Data Index: 876460 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2414. Min Act: -0.0000

Data Index: 293832 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2312. Min Act: -0.0000

Data Index: 451482 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1338705 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2220. Min Act: -0.0000

Data Index: 636144 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1204673 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.2190. Min Act: -0.0000

Data Index: 948713 (C4 (Web Text))

Max Activating Token Index: 110