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

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

Neuron 2883 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1029. Min Act: -0.0000

Data Index: 99094 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1055726 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1518243 (Python Code)

Max Activating Token Index: 1009

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1177900 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0845. Min Act: -0.0000

Data Index: 193128 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0854. Min Act: -0.0000

Data Index: 453316 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1227188 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0863. Min Act: -0.0001

Data Index: 896244 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0843. Min Act: -0.0000

Data Index: 819832 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0851. Min Act: -0.0000

Data Index: 385579 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0795. Min Act: -0.0001

Data Index: 836043 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0747. Min Act: -0.0001

Data Index: 907845 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0737. Min Act: -0.0001

Data Index: 538316 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1408530 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0733. Min Act: -0.0001

Data Index: 998814 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0777. Min Act: -0.0000

Data Index: 160184 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1337841 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0767. Min Act: -0.0000

Data Index: 229 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1308269 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0738. Min Act: -0.0000

Data Index: 343208 (C4 (Web Text))

Max Activating Token Index: 751