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

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

Neuron 4541 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: 0.8724. Min Range: -0.8724

Max Act: 0.8504. Min Act: -0.0000

Data Index: 378020 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1332657 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1357713 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7040. Min Act: -0.0000

Data Index: 957526 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1010532 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1186165 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6846. Min Act: -0.0000

Data Index: 248543 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6814. Min Act: -0.0000

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7062. Min Act: -0.0000

Data Index: 892595 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6865. Min Act: -0.0000

Data Index: 919869 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6694. Min Act: -0.0000

Data Index: 555998 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6703. Min Act: -0.0000

Data Index: 296479 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7443. Min Act: -0.0000

Data Index: 642309 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6081. Min Act: -0.0000

Data Index: 984530 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6089. Min Act: -0.0000

Data Index: 430225 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6290. Min Act: -0.0001

Data Index: 834412 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6225. Min Act: -0.0000

Data Index: 963282 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1199437 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6348. Min Act: -0.0000

Data Index: 274129 (C4 (Web Text))

Max Activating Token Index: 624