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

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

Neuron 2296 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5999. Min Act: -0.0001

Data Index: 124993 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5838. Min Act: -0.0001

Data Index: 1068972 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5517. Min Act: -0.0001

Data Index: 1111316 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5324. Min Act: -0.0000

Data Index: 593223 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5610. Min Act: -0.0000

Data Index: 433244 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5340. Min Act: -0.0000

Data Index: 127987 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5302. Min Act: -0.0000

Data Index: 14200 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1350295 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5385. Min Act: -0.0001

Data Index: 188940 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5185. Min Act: -0.0000

Data Index: 819889 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.5071. Min Act: -0.0000

Data Index: 268280 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4999. Min Act: -0.0000

Data Index: 592456 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4873. Min Act: -0.0001

Data Index: 769766 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4845. Min Act: -0.0000

Data Index: 134571 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4749. Min Act: -0.0000

Data Index: 298687 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4408. Min Act: -0.0001

Data Index: 84438 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4689. Min Act: -0.0001

Data Index: 1116270 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4989. Min Act: -0.0001

Data Index: 1024908 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1188426 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.5999. Min Range: -0.5999

Max Act: 0.4625. Min Act: -0.0001

Data Index: 433401 (C4 (Web Text))

Max Activating Token Index: 908