Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3546 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.7155. Min Act: -0.0001

Data Index: 217415 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6660. Min Act: -0.0001

Data Index: 124461 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6667. Min Act: -0.0002

Data Index: 51990 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6835. Min Act: -0.0001

Data Index: 925755 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6081. Min Act: -0.0002

Data Index: 777571 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5998. Min Act: -0.0001

Data Index: 491076 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6021. Min Act: -0.0002

Data Index: 594408 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6085. Min Act: -0.0001

Data Index: 854488 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5839. Min Act: -0.0001

Data Index: 158832 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5832. Min Act: -0.0001

Data Index: 838997 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5796. Min Act: -0.0001

Data Index: 1217008 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5537. Min Act: -0.0001

Data Index: 1321570 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5657. Min Act: -0.0001

Data Index: 2807 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5587. Min Act: -0.0002

Data Index: 1145592 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5537. Min Act: -0.0001

Data Index: 883938 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5535. Min Act: -0.0001

Data Index: 605856 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5531. Min Act: -0.0001

Data Index: 82309 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5696. Min Act: -0.0002

Data Index: 874659 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1066695 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1216833 (C4 (Web Text))

Max Activating Token Index: 822