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

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

Neuron 2308 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0001

Data Index: 319089 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0889. Min Act: -0.0001

Data Index: 638345 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1176414 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0869. Min Act: -0.0001

Data Index: 448228 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0869. Min Act: -0.0001

Data Index: 869455 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0787. Min Act: -0.0001

Data Index: 466697 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0856. Min Act: -0.0001

Data Index: 867007 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0785. Min Act: -0.0001

Data Index: 182093 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0747. Min Act: -0.0001

Data Index: 393538 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0754. Min Act: -0.0001

Data Index: 319228 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0763. Min Act: -0.0001

Data Index: 82844 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0771. Min Act: -0.0001

Data Index: 588735 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0700. Min Act: -0.0001

Data Index: 499386 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0745. Min Act: -0.0001

Data Index: 730328 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0746. Min Act: -0.0001

Data Index: 282531 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1126516 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0708. Min Act: -0.0001

Data Index: 637682 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0729. Min Act: -0.0001

Data Index: 354507 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0731. Min Act: -0.0001

Data Index: 26509 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1102159 (C4 (Web Text))

Max Activating Token Index: 82