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

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

Neuron 2460 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5522. Min Act: -0.0001

Data Index: 875706 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1165731 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5689. Min Act: -0.0001

Data Index: 774649 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4560. Min Act: -0.0001

Data Index: 617190 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4654. Min Act: -0.0001

Data Index: 1084243 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4704. Min Act: -0.0001

Data Index: 1048768 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4356. Min Act: -0.0001

Data Index: 724392 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4226. Min Act: -0.0001

Data Index: 180829 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4220. Min Act: -0.0001

Data Index: 1253857 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4428. Min Act: -0.0001

Data Index: 107669 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4580. Min Act: -0.0001

Data Index: 875875 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4119. Min Act: -0.0001

Data Index: 385356 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3922. Min Act: -0.0001

Data Index: 174002 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3902. Min Act: -0.0001

Data Index: 285034 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3823. Min Act: -0.0001

Data Index: 525182 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4031. Min Act: -0.0001

Data Index: 855880 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3990. Min Act: -0.0001

Data Index: 34 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3972. Min Act: -0.0001

Data Index: 1348633 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1215497 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3948. Min Act: -0.0001

Data Index: 237686 (C4 (Web Text))

Max Activating Token Index: 475