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

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

Neuron 831 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1304450 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1337. Min Act: -0.0000

Data Index: 177438 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1043. Min Act: -0.0000

Data Index: 256531 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1064. Min Act: -0.0000

Data Index: 273236 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1129637 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1112452 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1105. Min Act: -0.0000

Data Index: 745405 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0932. Min Act: -0.0000

Data Index: 950335 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0934. Min Act: -0.0001

Data Index: 809608 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0888. Min Act: -0.0000

Data Index: 320858 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0975. Min Act: -0.0000

Data Index: 232202 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0937. Min Act: -0.0000

Data Index: 340131 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0957. Min Act: -0.0000

Data Index: 605658 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1212697 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1117402 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0848. Min Act: -0.0000

Data Index: 109580 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0845. Min Act: -0.0000

Data Index: 674926 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0840. Min Act: -0.0000

Data Index: 25781 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1055153 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1179108 (C4 (Web Text))

Max Activating Token Index: 746