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

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

Neuron 1956 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: 0.4237. Min Range: -0.4237

Max Act: 0.3842. Min Act: -0.0002

Data Index: 466082 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3904. Min Act: -0.0001

Data Index: 122038 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.4237. Min Act: -0.0001

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3753. Min Act: -0.0002

Data Index: 859193 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3440. Min Act: -0.0002

Data Index: 663707 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.4043. Min Act: -0.0002

Data Index: 1138124 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3830. Min Act: -0.0002

Data Index: 427204 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3673. Min Act: -0.0002

Data Index: 200776 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1012123 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3772. Min Act: -0.0001

Data Index: 1121783 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3667. Min Act: -0.0002

Data Index: 1068717 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3905. Min Act: -0.0002

Data Index: 1049598 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3772. Min Act: -0.0002

Data Index: 1012471 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1318385 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1179131 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3463. Min Act: -0.0002

Data Index: 974469 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3487. Min Act: -0.0002

Data Index: 314864 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3607. Min Act: -0.0002

Data Index: 830728 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3889. Min Act: -0.0002

Data Index: 472906 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3588. Min Act: -0.0002

Data Index: 263046 (C4 (Web Text))

Max Activating Token Index: 1012