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

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

Neuron 965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8770. Min Act: -0.0000

Data Index: 271810 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.9068. Min Act: 0.0000

Data Index: 288828 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8993. Min Act: 0.0000

Data Index: 511835 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8657. Min Act: -0.0000

Data Index: 797486 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1145114 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7949. Min Act: -0.0000

Data Index: 392250 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1176028 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8005. Min Act: -0.0000

Data Index: 468730 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1024827 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1088156 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1031038 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7873. Min Act: -0.0000

Data Index: 773125 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7645. Min Act: -0.0000

Data Index: 387335 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7562. Min Act: -0.0000

Data Index: 807363 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7281. Min Act: 0.0000

Data Index: 1295626 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7247. Min Act: -0.0000

Data Index: 849038 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1006739 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.6998. Min Act: -0.0000

Data Index: 840941 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7115. Min Act: -0.0000

Data Index: 448482 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7204. Min Act: -0.0000

Data Index: 566162 (C4 (Web Text))

Max Activating Token Index: 523