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

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

Neuron 1584 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.5324. Min Act: -0.0002

Data Index: 48423 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4309. Min Act: -0.0002

Data Index: 764355 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4636. Min Act: -0.0002

Data Index: 613168 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4454. Min Act: -0.0002

Data Index: 578866 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4480. Min Act: -0.0002

Data Index: 53968 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4755. Min Act: -0.0002

Data Index: 974616 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4595. Min Act: -0.0002

Data Index: 494794 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4098. Min Act: -0.0002

Data Index: 688262 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3939. Min Act: -0.0002

Data Index: 876999 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4123. Min Act: -0.0002

Data Index: 1330336 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4383. Min Act: -0.0002

Data Index: 1194680 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4189. Min Act: -0.0002

Data Index: 914961 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4365. Min Act: -0.0002

Data Index: 1031771 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3839. Min Act: -0.0002

Data Index: 832752 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4363. Min Act: -0.0002

Data Index: 534158 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4545. Min Act: -0.0002

Data Index: 965158 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4521. Min Act: -0.0002

Data Index: 120881 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4101. Min Act: -0.0002

Data Index: 1084569 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3771. Min Act: -0.0002

Data Index: 1330120 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4028. Min Act: -0.0002

Data Index: 1946 (C4 (Web Text))

Max Activating Token Index: 746