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

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

Neuron 5903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8099. Min Range: -2.8099

Max Act: 2.8099. Min Act: -0.0000

Data Index: 574093 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 2.8099. Min Range: -2.8099

Max Act: 2.7575. Min Act: -0.0000

Data Index: 399013 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 2.8099. Min Range: -2.8099

Max Act: 2.2741. Min Act: -0.0000

Data Index: 151424 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.8990. Min Act: -0.0000

Data Index: 805716 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.8519. Min Act: -0.0000

Data Index: 955643 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.8039. Min Act: -0.0000

Data Index: 1148282 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.7725. Min Act: -0.0000

Data Index: 974102 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1036030 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.7031. Min Act: -0.0000

Data Index: 261566 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.7033. Min Act: -0.0000

Data Index: 1157036 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.7891. Min Act: -0.0000

Data Index: 103860 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6910. Min Act: -0.0000

Data Index: 237075 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6612. Min Act: -0.0000

Data Index: 570319 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6487. Min Act: -0.0000

Data Index: 333190 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1081712 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6277. Min Act: -0.0000

Data Index: 1289509 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.5378. Min Act: -0.0000

Data Index: 1231321 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6093. Min Act: -0.0000

Data Index: 281894 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6206. Min Act: -0.0000

Data Index: 199112 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 2.8099. Min Range: -2.8099

Max Act: 1.6972. Min Act: -0.0000

Data Index: 810073 (C4 (Web Text))

Max Activating Token Index: 866