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

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

Neuron 4082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.7675. Min Act: -0.0000

Data Index: 988609 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1083675 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3088. Min Act: -0.0000

Data Index: 341653 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1249005 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.1269. Min Act: -0.0000

Data Index: 839775 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.0437. Min Act: -0.0000

Data Index: 862968 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.0212. Min Act: -0.0000

Data Index: 377696 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.9856. Min Act: -0.0000

Data Index: 910726 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.0334. Min Act: -0.0000

Data Index: 486508 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.9706. Min Act: -0.0000

Data Index: 120246 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1216168 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1253925 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1198470 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.9770. Min Act: -0.0000

Data Index: 437114 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.8965. Min Act: -0.0000

Data Index: 442503 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.8717. Min Act: -0.0000

Data Index: 367822 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.8512. Min Act: -0.0000

Data Index: 478946 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1323287 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.7564. Min Act: -0.0000

Data Index: 805688 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 1.7675. Min Range: -1.7675

Max Act: 0.8009. Min Act: -0.0000

Data Index: 971101 (C4 (Web Text))

Max Activating Token Index: 352