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

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

Neuron 2451 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.8809. Min Act: -0.0000

Data Index: 1318790 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.8167. Min Act: -0.0000

Data Index: 186889 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6167. Min Act: -0.0000

Data Index: 236246 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.7721. Min Act: -0.0000

Data Index: 828208 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.7667. Min Act: -0.0000

Data Index: 1105816 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.7118. Min Act: -0.0000

Data Index: 645806 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 2.0355. Min Range: -2.0355

Max Act: 2.0355. Min Act: -0.0000

Data Index: 312356 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6909. Min Act: -0.0000

Data Index: 759075 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6847. Min Act: -0.0000

Data Index: 171221 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6957. Min Act: -0.0000

Data Index: 1245956 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.5760. Min Act: -0.0000

Data Index: 1321226 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.5526. Min Act: -0.0000

Data Index: 130612 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6041. Min Act: -0.0000

Data Index: 884414 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6819. Min Act: -0.0000

Data Index: 670681 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.5732. Min Act: -0.0000

Data Index: 30658 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6392. Min Act: -0.0000

Data Index: 108838 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.3739. Min Act: -0.0000

Data Index: 403855 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.4584. Min Act: -0.0000

Data Index: 337528 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.6208. Min Act: -0.0000

Data Index: 1303960 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 2.0355. Min Range: -2.0355

Max Act: 1.5274. Min Act: -0.0000

Data Index: 477200 (C4 (Web Text))

Max Activating Token Index: 857