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

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

Neuron 3076 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.4648. Min Act: -0.0001

Data Index: 650621 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3114. Min Act: -0.0001

Data Index: 1263444 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3258. Min Act: -0.0000

Data Index: 132153 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2694. Min Act: -0.0000

Data Index: 59774 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.0858. Min Act: -0.0001

Data Index: 272121 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.1138. Min Act: -0.0001

Data Index: 359119 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.1571. Min Act: -0.0001

Data Index: 1089823 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.0524. Min Act: -0.0001

Data Index: 702524 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1301824 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.0654. Min Act: -0.0001

Data Index: 128453 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.0319. Min Act: -0.0001

Data Index: 743060 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1311952 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9858. Min Act: -0.0001

Data Index: 122013 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9926. Min Act: -0.0001

Data Index: 1091594 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1011399 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9815. Min Act: -0.0000

Data Index: 532890 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9786. Min Act: -0.0000

Data Index: 219752 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9427. Min Act: -0.0000

Data Index: 737418 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9837. Min Act: -0.0001

Data Index: 777357 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9458. Min Act: -0.0001

Data Index: 759053 (C4 (Web Text))

Max Activating Token Index: 994