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

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

Neuron 1265 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1341273 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5477. Min Act: -0.0000

Data Index: 471328 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5495. Min Act: -0.0000

Data Index: 359958 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1031590 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4504. Min Act: -0.0000

Data Index: 522487 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4074. Min Act: 0.0000

Data Index: 985551 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4242. Min Act: -0.0000

Data Index: 944913 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3996. Min Act: -0.0000

Data Index: 679292 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1317875 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1083067 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3663. Min Act: -0.0000

Data Index: 635813 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1140984 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3490. Min Act: -0.0000

Data Index: 99406 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3584. Min Act: -0.0000

Data Index: 671816 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3785. Min Act: -0.0000

Data Index: 495436 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1165434 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1056888 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3525. Min Act: -0.0000

Data Index: 397111 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3474. Min Act: 0.0000

Data Index: 478077 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.3551. Min Act: -0.0000

Data Index: 481874 (C4 (Web Text))

Max Activating Token Index: 527