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

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

Neuron 3391 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: 1.3737. Min Range: -1.3737

Max Act: 1.3737. Min Act: -0.0000

Data Index: 138683 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1237102 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0798. Min Act: -0.0000

Data Index: 111510 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9768. Min Act: -0.0000

Data Index: 644948 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9295. Min Act: -0.0000

Data Index: 966016 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1107046 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8784. Min Act: -0.0000

Data Index: 280837 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1012315 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1154577 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8387. Min Act: -0.0000

Data Index: 62296 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7126. Min Act: -0.0000

Data Index: 332172 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7840. Min Act: -0.0000

Data Index: 794530 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7287. Min Act: -0.0000

Data Index: 454134 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7707. Min Act: -0.0000

Data Index: 282867 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7220. Min Act: -0.0000

Data Index: 819247 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1214586 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1157851 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.6910. Min Act: -0.0000

Data Index: 235680 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7116. Min Act: -0.0000

Data Index: 266160 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.6690. Min Act: -0.0000

Data Index: 857523 (C4 (Web Text))

Max Activating Token Index: 406