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

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

Neuron 4189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5966. Min Range: -6.5966

Max Act: 6.5966. Min Act: -0.0000

Data Index: 709193 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 6.5966. Min Range: -6.5966

Max Act: 5.2407. Min Act: -0.0000

Data Index: 1171409 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 6.5966. Min Range: -6.5966

Max Act: 5.2367. Min Act: -0.0000

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.9848. Min Act: -0.0000

Data Index: 1036429 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.8054. Min Act: -0.0000

Data Index: 862797 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.6354. Min Act: -0.0000

Data Index: 760599 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.8152. Min Act: -0.0000

Data Index: 1156190 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.3515. Min Act: -0.0000

Data Index: 962787 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.6534. Min Act: -0.0000

Data Index: 544382 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.4720. Min Act: -0.0000

Data Index: 410163 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.6136. Min Act: -0.0000

Data Index: 958441 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.7662. Min Act: -0.0000

Data Index: 996230 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.3803. Min Act: -0.0000

Data Index: 433263 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.3210. Min Act: -0.0000

Data Index: 56850 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.4774. Min Act: -0.0000

Data Index: 550448 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.4568. Min Act: -0.0000

Data Index: 747003 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.2011. Min Act: -0.0000

Data Index: 1016739 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.3399. Min Act: -0.0000

Data Index: 369956 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.3365. Min Act: -0.0000

Data Index: 392763 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 6.5966. Min Range: -6.5966

Max Act: 4.4916. Min Act: -0.0000

Data Index: 809532 (C4 (Web Text))

Max Activating Token Index: 136