Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3661 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.5134. Min Act: -0.0002

Data Index: 1208639 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4895. Min Act: -0.0002

Data Index: 612369 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4896. Min Act: -0.0002

Data Index: 980063 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4540. Min Act: -0.0001

Data Index: 1355368 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4937. Min Act: -0.0002

Data Index: 388704 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4921. Min Act: -0.0002

Data Index: 316789 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4850. Min Act: -0.0002

Data Index: 920270 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4831. Min Act: -0.0002

Data Index: 340586 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4458. Min Act: -0.0002

Data Index: 805605 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4525. Min Act: -0.0002

Data Index: 1188904 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4631. Min Act: -0.0002

Data Index: 504295 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4617. Min Act: -0.0001

Data Index: 138833 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4620. Min Act: -0.0002

Data Index: 1276403 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4596. Min Act: -0.0002

Data Index: 303031 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4412. Min Act: -0.0002

Data Index: 562323 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4391. Min Act: -0.0001

Data Index: 1183265 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4477. Min Act: -0.0002

Data Index: 1037768 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4328. Min Act: -0.0002

Data Index: 1357885 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4486. Min Act: -0.0002

Data Index: 142044 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4446. Min Act: -0.0002

Data Index: 76767 (C4 (Web Text))

Max Activating Token Index: 331