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

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

Neuron 2894 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 326710 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1166945 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 95632 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 120393 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 712087 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 880383 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 776581 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 602133 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 988770 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1361571 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1500688 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 328093 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 801188 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 746803 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 100781 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1100964 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 95837 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 584952 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 694057 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 655090 (C4 (Web Text))

Max Activating Token Index: 388