Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 35 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0006

Data Index: 583202 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0805. Min Act: -0.0006

Data Index: 1335790 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0735. Min Act: -0.0006

Data Index: 326942 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0693. Min Act: -0.0006

Data Index: 160148 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0707. Min Act: -0.0006

Data Index: 129871 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0692. Min Act: -0.0006

Data Index: 872086 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0689. Min Act: -0.0006

Data Index: 1297193 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0681. Min Act: -0.0006

Data Index: 6831 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0670. Min Act: -0.0006

Data Index: 977190 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0653. Min Act: -0.0006

Data Index: 1186428 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0639. Min Act: -0.0006

Data Index: 998743 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0673. Min Act: -0.0006

Data Index: 999272 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0648. Min Act: -0.0006

Data Index: 1150168 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0609. Min Act: -0.0006

Data Index: 1353385 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0649. Min Act: -0.0006

Data Index: 507976 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0630. Min Act: -0.0006

Data Index: 1150765 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0615. Min Act: -0.0006

Data Index: 1326678 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0598. Min Act: -0.0006

Data Index: 973432 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0587. Min Act: -0.0006

Data Index: 529086 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0621. Min Act: -0.0006

Data Index: 962435 (C4 (Web Text))

Max Activating Token Index: 215