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

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

Neuron 1175 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: 4.7453. Min Range: -4.7453

Max Act: 4.7453. Min Act: -0.0002

Data Index: 1242201 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 4.7453. Min Range: -4.7453

Max Act: 4.3118. Min Act: -0.0002

Data Index: 65102 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 4.7453. Min Range: -4.7453

Max Act: 4.6714. Min Act: -0.0002

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.7543. Min Act: -0.0002

Data Index: 508454 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 4.7453. Min Range: -4.7453

Max Act: 4.4648. Min Act: -0.0002

Data Index: 961513 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 4.7453. Min Range: -4.7453

Max Act: 4.2801. Min Act: -0.0002

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.5025. Min Act: -0.0002

Data Index: 841806 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.8686. Min Act: -0.0002

Data Index: 410360 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.9799. Min Act: -0.0002

Data Index: 768790 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.9576. Min Act: -0.0002

Data Index: 438710 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.8452. Min Act: -0.0002

Data Index: 809645 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.8268. Min Act: -0.0002

Data Index: 422028 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 4.7453. Min Range: -4.7453

Max Act: 4.3148. Min Act: -0.0002

Data Index: 309108 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.6227. Min Act: -0.0001

Data Index: 1055013 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.3012. Min Act: -0.0002

Data Index: 264139 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.7302. Min Act: -0.0002

Data Index: 837989 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.8465. Min Act: -0.0001

Data Index: 674166 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.9540. Min Act: -0.0002

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 4.7453. Min Range: -4.7453

Max Act: 3.5642. Min Act: -0.0001

Data Index: 957231 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 4.7453. Min Range: -4.7453

Max Act: 4.1886. Min Act: -0.0002

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 141