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

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

Neuron 3138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.3429. Min Act: -0.0000

Data Index: 925455 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.3742. Min Act: -0.0000

Data Index: 79188 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.2815. Min Act: -0.0000

Data Index: 110779 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.2091. Min Act: -0.0000

Data Index: 758179 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1116116 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1096955 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.2623. Min Act: -0.0000

Data Index: 181981 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.1813. Min Act: -0.0000

Data Index: 619870 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.1598. Min Act: -0.0000

Data Index: 569587 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.1356. Min Act: -0.0000

Data Index: 610568 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0827. Min Act: -0.0000

Data Index: 995483 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0873. Min Act: -0.0000

Data Index: 414954 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1115737 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0543. Min Act: -0.0000

Data Index: 487383 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0499. Min Act: -0.0000

Data Index: 41752 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1300171 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0000. Min Act: -0.0000

Data Index: 474521 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.3742. Min Range: -1.3742

Max Act: 1.0151. Min Act: -0.0000

Data Index: 71557 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.3742. Min Range: -1.3742

Max Act: 0.9548. Min Act: -0.0000

Data Index: 3325 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.3742. Min Range: -1.3742

Max Act: 0.9770. Min Act: -0.0000

Data Index: 905311 (C4 (Web Text))

Max Activating Token Index: 186