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

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

Neuron 3690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.7578. Min Act: -0.0000

Data Index: 217323 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5755. Min Act: -0.0000

Data Index: 1067007 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5393. Min Act: -0.0000

Data Index: 125262 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5316. Min Act: -0.0000

Data Index: 764784 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1581066 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5339. Min Act: -0.0000

Data Index: 172389 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4944. Min Act: -0.0000

Data Index: 450487 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1263483 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4657. Min Act: -0.0000

Data Index: 285275 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4546. Min Act: -0.0000

Data Index: 311967 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5783. Min Act: -0.0000

Data Index: 289273 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.5419. Min Act: -0.0000

Data Index: 23491 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4330. Min Act: -0.0000

Data Index: 130075 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4827. Min Act: -0.0000

Data Index: 553842 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4005. Min Act: -0.0000

Data Index: 33134 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4020. Min Act: -0.0000

Data Index: 834919 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4252. Min Act: -0.0000

Data Index: 791226 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.3820. Min Act: -0.0000

Data Index: 828718 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4585. Min Act: -0.0000

Data Index: 777784 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.7578. Min Range: -1.7578

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1098714 (C4 (Web Text))

Max Activating Token Index: 183