Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4375 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5985. Min Act: -0.0000

Data Index: 281048 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5596. Min Act: -0.0000

Data Index: 774068 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4928. Min Act: -0.0000

Data Index: 591031 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1162140 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4673. Min Act: -0.0000

Data Index: 927120 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4645. Min Act: -0.0000

Data Index: 7871 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1204980 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1221670 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4094. Min Act: -0.0000

Data Index: 315458 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4077. Min Act: -0.0000

Data Index: 761906 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4106. Min Act: -0.0000

Data Index: 520244 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4357. Min Act: -0.0000

Data Index: 775669 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1187811 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4043. Min Act: 0.0000

Data Index: 1312099 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3897. Min Act: -0.0000

Data Index: 785621 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3842. Min Act: -0.0000

Data Index: 37308 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1149570 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3838. Min Act: -0.0000

Data Index: 231529 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3803. Min Act: -0.0000

Data Index: 130896 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3702. Min Act: -0.0000

Data Index: 46841 (C4 (Web Text))

Max Activating Token Index: 761