Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3351 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.9945. Min Act: -0.0000

Data Index: 782061 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.9284. Min Act: -0.0000

Data Index: 600949 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 2.0380. Min Range: -2.0380

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1067242 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1097903 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7709. Min Act: -0.0001

Data Index: 1333464 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7214. Min Act: -0.0001

Data Index: 1197196 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7385. Min Act: -0.0000

Data Index: 350344 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1216167 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.8087. Min Act: -0.0000

Data Index: 1077370 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7089. Min Act: -0.0000

Data Index: 252793 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7049. Min Act: -0.0000

Data Index: 291440 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7095. Min Act: -0.0000

Data Index: 275550 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.6962. Min Act: -0.0000

Data Index: 213152 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.7261. Min Act: -0.0000

Data Index: 126719 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.5968. Min Act: -0.0000

Data Index: 1323114 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.8612. Min Act: -0.0000

Data Index: 129381 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.6701. Min Act: -0.0000

Data Index: 822376 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1160185 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.4955. Min Act: -0.0000

Data Index: 625862 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.0380. Min Range: -2.0380

Max Act: 1.6245. Min Act: -0.0000

Data Index: 786019 (C4 (Web Text))

Max Activating Token Index: 132