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

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

Neuron 508 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: 0.5081. Min Range: -0.5081

Max Act: 0.5081. Min Act: -0.0000

Data Index: 839072 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4270. Min Act: -0.0000

Data Index: 832353 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4574. Min Act: -0.0000

Data Index: 369830 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4383. Min Act: -0.0000

Data Index: 612745 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1044490 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3891. Min Act: -0.0000

Data Index: 688206 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4185. Min Act: -0.0000

Data Index: 818415 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3988. Min Act: -0.0000

Data Index: 123819 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1100695 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1175980 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1037252 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1298936 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3365. Min Act: -0.0000

Data Index: 112543 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3762. Min Act: -0.0000

Data Index: 970959 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3945. Min Act: -0.0000

Data Index: 653675 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1038774 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3719. Min Act: -0.0000

Data Index: 898917 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3323. Min Act: -0.0000

Data Index: 252960 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1084715 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3346. Min Act: -0.0000

Data Index: 406268 (C4 (Web Text))

Max Activating Token Index: 809