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

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

Neuron 4372 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: 1.4742. Min Range: -1.4742

Max Act: 1.4742. Min Act: -0.0000

Data Index: 2924 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2053. Min Act: -0.0000

Data Index: 174749 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2005. Min Act: -0.0000

Data Index: 398861 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1038565 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1027. Min Act: -0.0000

Data Index: 54460 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1186997 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9452. Min Act: -0.0000

Data Index: 865771 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9908. Min Act: -0.0000

Data Index: 475674 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9395. Min Act: -0.0000

Data Index: 387471 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8066. Min Act: -0.0000

Data Index: 559740 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8412. Min Act: -0.0000

Data Index: 300346 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8954. Min Act: -0.0000

Data Index: 179634 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1040947 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8472. Min Act: -0.0000

Data Index: 443173 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8014. Min Act: -0.0000

Data Index: 443816 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8023. Min Act: -0.0000

Data Index: 978856 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.7560. Min Act: -0.0000

Data Index: 15368 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.7982. Min Act: -0.0000

Data Index: 720702 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8749. Min Act: -0.0000

Data Index: 593052 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8394. Min Act: -0.0000

Data Index: 554320 (C4 (Web Text))

Max Activating Token Index: 1003