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

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

Neuron 6066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.7040. Min Act: -0.0000

Data Index: 494 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.6475. Min Act: -0.0000

Data Index: 101004 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.1604. Min Act: -0.0000

Data Index: 392859 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.0966. Min Act: -0.0000

Data Index: 423417 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.0095. Min Act: -0.0000

Data Index: 33939 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.1858. Min Act: -0.0000

Data Index: 53099 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.6284. Min Act: -0.0000

Data Index: 933286 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.4657. Min Act: -0.0000

Data Index: 66768 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.5040. Min Act: -0.0000

Data Index: 520324 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.1113. Min Act: -0.0000

Data Index: 1212977 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.3286. Min Act: -0.0000

Data Index: 32745 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.2589. Min Act: -0.0000

Data Index: 237708 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.2311. Min Act: -0.0000

Data Index: 1200521 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.0849. Min Act: -0.0000

Data Index: 503989 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.3669. Min Act: -0.0000

Data Index: 159988 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.1752. Min Act: -0.0000

Data Index: 978537 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 4.7040. Min Range: -4.7040

Max Act: 3.1468. Min Act: -0.0000

Data Index: 1135857 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 4.7040. Min Range: -4.7040

Max Act: 2.9829. Min Act: -0.0000

Data Index: 256715 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 4.7040. Min Range: -4.7040

Max Act: 2.9900. Min Act: -0.0000

Data Index: 810111 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 4.7040. Min Range: -4.7040

Max Act: 2.9883. Min Act: -0.0000

Data Index: 1085034 (C4 (Web Text))

Max Activating Token Index: 371