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

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

Neuron 5793 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: 5.7821. Min Range: -5.7821

Max Act: 5.7821. Min Act: -0.0000

Data Index: 886203 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 5.7821. Min Range: -5.7821

Max Act: 5.5789. Min Act: -0.0000

Data Index: 652004 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 5.7821. Min Range: -5.7821

Max Act: 5.4006. Min Act: -0.0000

Data Index: 42543 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 5.7821. Min Range: -5.7821

Max Act: 5.6959. Min Act: -0.0000

Data Index: 802019 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 5.7821. Min Range: -5.7821

Max Act: 5.4419. Min Act: -0.0000

Data Index: 587053 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 5.7821. Min Range: -5.7821

Max Act: 5.1450. Min Act: -0.0000

Data Index: 1278840 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.7410. Min Act: -0.0000

Data Index: 1095763 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.7886. Min Act: -0.0000

Data Index: 598701 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.7705. Min Act: -0.0000

Data Index: 264448 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.7232. Min Act: -0.0000

Data Index: 30616 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.8867. Min Act: -0.0000

Data Index: 413261 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.6859. Min Act: -0.0000

Data Index: 363423 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.8056. Min Act: -0.0000

Data Index: 848443 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.9497. Min Act: -0.0000

Data Index: 719605 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.6342. Min Act: -0.0000

Data Index: 59404 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.5803. Min Act: -0.0000

Data Index: 1052736 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.5570. Min Act: -0.0000

Data Index: 461775 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.7815. Min Act: -0.0000

Data Index: 61949 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.4934. Min Act: -0.0000

Data Index: 925053 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 5.7821. Min Range: -5.7821

Max Act: 4.5180. Min Act: -0.0000

Data Index: 789457 (C4 (Web Text))

Max Activating Token Index: 78