Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2976 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0001

Data Index: 144003 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1032013 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1017. Min Act: -0.0001

Data Index: 304336 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1046815 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1036. Min Act: -0.0001

Data Index: 180957 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0980. Min Act: -0.0001

Data Index: 476304 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0937. Min Act: -0.0001

Data Index: 764213 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0912. Min Act: -0.0000

Data Index: 558163 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0907. Min Act: -0.0001

Data Index: 424446 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1044978 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0878. Min Act: -0.0001

Data Index: 18920 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0856. Min Act: -0.0001

Data Index: 131351 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0880. Min Act: 0.0000

Data Index: 1354312 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0838. Min Act: -0.0001

Data Index: 91705 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0839. Min Act: -0.0001

Data Index: 648284 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0822. Min Act: -0.0001

Data Index: 801355 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0812. Min Act: -0.0001

Data Index: 425230 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0809. Min Act: -0.0000

Data Index: 739826 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0787. Min Act: -0.0001

Data Index: 220964 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0777. Min Act: -0.0001

Data Index: 459952 (C4 (Web Text))

Max Activating Token Index: 870