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

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

Neuron 5568 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: 2.2987. Min Range: -2.2987

Max Act: 2.2987. Min Act: -0.0000

Data Index: 906894 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.2987. Min Range: -2.2987

Max Act: 2.0481. Min Act: -0.0000

Data Index: 724778 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.9034. Min Act: -0.0000

Data Index: 739567 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.8054. Min Act: -0.0000

Data Index: 545378 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.8508. Min Act: -0.0000

Data Index: 390738 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.8365. Min Act: -0.0000

Data Index: 949739 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.8028. Min Act: -0.0000

Data Index: 332839 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.7364. Min Act: -0.0000

Data Index: 661909 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1257996 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6953. Min Act: -0.0000

Data Index: 361982 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6597. Min Act: -0.0000

Data Index: 455928 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6787. Min Act: -0.0000

Data Index: 959812 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6558. Min Act: -0.0000

Data Index: 706162 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6218. Min Act: -0.0000

Data Index: 887092 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6195. Min Act: -0.0000

Data Index: 1145222 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6085. Min Act: -0.0000

Data Index: 957177 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.6956. Min Act: -0.0000

Data Index: 1251075 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.5875. Min Act: -0.0000

Data Index: 813005 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.5717. Min Act: -0.0000

Data Index: 522028 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 2.2987. Min Range: -2.2987

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1179586 (C4 (Web Text))

Max Activating Token Index: 1013