Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2372 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.4309. Min Act: -0.0001

Data Index: 561769 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.3551. Min Act: -0.0001

Data Index: 294961 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.1446. Min Act: -0.0001

Data Index: 576520 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9936. Min Act: -0.0001

Data Index: 499816 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.0102. Min Act: -0.0001

Data Index: 183782 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9490. Min Act: -0.0001

Data Index: 963105 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9636. Min Act: -0.0001

Data Index: 600320 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9807. Min Act: -0.0001

Data Index: 397553 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9429. Min Act: -0.0001

Data Index: 808353 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.0285. Min Act: -0.0001

Data Index: 298920 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8761. Min Act: -0.0001

Data Index: 17482 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1101608 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8916. Min Act: -0.0001

Data Index: 10043 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7759. Min Act: -0.0001

Data Index: 421805 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8677. Min Act: -0.0001

Data Index: 19662 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8218. Min Act: -0.0001

Data Index: 544385 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8752. Min Act: -0.0001

Data Index: 346703 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8031. Min Act: -0.0001

Data Index: 647023 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7868. Min Act: -0.0001

Data Index: 84325 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7915. Min Act: -0.0001

Data Index: 662444 (C4 (Web Text))

Max Activating Token Index: 759