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

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

Neuron 3129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1110176 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1058010 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8821. Min Act: -0.0000

Data Index: 530990 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8776. Min Act: -0.0000

Data Index: 509127 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8483. Min Act: -0.0000

Data Index: 525882 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8760. Min Act: -0.0000

Data Index: 978381 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9059. Min Act: -0.0000

Data Index: 820145 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8473. Min Act: -0.0000

Data Index: 198854 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8212. Min Act: -0.0000

Data Index: 924418 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1191582 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7944. Min Act: -0.0000

Data Index: 55893 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1231045 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8524. Min Act: -0.0000

Data Index: 99179 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7908. Min Act: -0.0000

Data Index: 777225 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1291616 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8035. Min Act: -0.0000

Data Index: 57382 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7957. Min Act: -0.0000

Data Index: 915246 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8028. Min Act: -0.0000

Data Index: 503274 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7929. Min Act: -0.0000

Data Index: 937254 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8096. Min Act: -0.0000

Data Index: 389202 (C4 (Web Text))

Max Activating Token Index: 286