Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1330577 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0732. Min Act: -0.0000

Data Index: 75220 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0000

Data Index: 908449 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0732. Min Act: -0.0000

Data Index: 316651 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0689. Min Act: -0.0000

Data Index: 364013 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0711. Min Act: -0.0000

Data Index: 612134 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0716. Min Act: -0.0000

Data Index: 221846 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0693. Min Act: -0.0000

Data Index: 493571 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0687. Min Act: -0.0000

Data Index: 409489 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0642. Min Act: -0.0000

Data Index: 297 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0687. Min Act: -0.0000

Data Index: 270931 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0655. Min Act: -0.0000

Data Index: 691007 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0653. Min Act: -0.0000

Data Index: 40732 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0672. Min Act: -0.0000

Data Index: 78173 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1346657 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0649. Min Act: -0.0000

Data Index: 986572 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1019425 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1117563 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0652. Min Act: -0.0000

Data Index: 355438 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1043145 (C4 (Web Text))

Max Activating Token Index: 246