Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4637 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.5578. Min Act: -0.0000

Data Index: 622851 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1195780 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2499. Min Act: -0.0000

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.3692. Min Act: -0.0000

Data Index: 623502 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1235355 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.3099. Min Act: -0.0000

Data Index: 372568 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2154. Min Act: -0.0000

Data Index: 640975 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2249. Min Act: -0.0000

Data Index: 706131 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.5863. Min Range: -1.5863

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1209442 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2663. Min Act: -0.0000

Data Index: 72028 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1049. Min Act: -0.0000

Data Index: 467258 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1327427 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1221132 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1402. Min Act: -0.0000

Data Index: 704418 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0351. Min Act: -0.0000

Data Index: 790981 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 1.5863. Min Range: -1.5863

Max Act: 0.9719. Min Act: -0.0000

Data Index: 159102 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0550. Min Act: -0.0000

Data Index: 873057 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0903. Min Act: -0.0000

Data Index: 887910 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0412. Min Act: -0.0000

Data Index: 187330 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0014. Min Act: -0.0000

Data Index: 203946 (C4 (Web Text))

Max Activating Token Index: 372