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

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

Neuron 5018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1696. Min Range: -2.1696

Max Act: 2.1696. Min Act: -0.0000

Data Index: 1026068 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 2.1696. Min Range: -2.1696

Max Act: 2.1104. Min Act: -0.0000

Data Index: 789648 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8938. Min Act: -0.0000

Data Index: 128939 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.9187. Min Act: -0.0000

Data Index: 894143 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.9291. Min Act: -0.0000

Data Index: 891018 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.3675. Min Act: -0.0000

Data Index: 220037 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8086. Min Act: -0.0000

Data Index: 696382 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1239530 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6346. Min Act: -0.0000

Data Index: 291432 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1135079 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7591. Min Act: -0.0000

Data Index: 315927 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6752. Min Act: -0.0000

Data Index: 1276842 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1299282 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7358. Min Act: -0.0000

Data Index: 118874 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8229. Min Act: -0.0001

Data Index: 1121414 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.4624. Min Act: -0.0000

Data Index: 650832 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.3627. Min Act: -0.0000

Data Index: 125835 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6800. Min Act: -0.0000

Data Index: 959207 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6734. Min Act: -0.0000

Data Index: 171212 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6587. Min Act: -0.0000

Data Index: 79373 (C4 (Web Text))

Max Activating Token Index: 654