Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1435 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0042. Min Act: -0.0003

Data Index: 665255 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0037. Min Act: -0.0004

Data Index: 916512 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0003

Data Index: 503663 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0004

Data Index: 278932 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0004

Data Index: 380614 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0003

Data Index: 179570 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1543839 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0004

Data Index: 1267967 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0004

Data Index: 818745 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0004

Data Index: 718088 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0004

Data Index: 957081 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1647831 (Python Code)

Max Activating Token Index: 286

Text #12

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0036. Min Act: -0.0003

Data Index: 863457 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0004

Data Index: 1200911 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1569739 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0003

Data Index: 203156 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0003

Data Index: 248590 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0004

Data Index: 892936 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0003

Data Index: 676928 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1078073 (C4 (Web Text))

Max Activating Token Index: 951