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

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

Neuron 2235 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1149. Min Range: -5.1149

Max Act: 5.1149. Min Act: -0.0000

Data Index: 971984 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.9078. Min Act: -0.0000

Data Index: 448686 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.9383. Min Act: -0.0000

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.4956. Min Act: -0.0000

Data Index: 142163 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.3435. Min Act: -0.0000

Data Index: 1183311 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.3043. Min Act: -0.0000

Data Index: 483365 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.1201. Min Act: -0.0000

Data Index: 935772 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.1149. Min Act: -0.0000

Data Index: 460253 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 5.1149. Min Range: -5.1149

Max Act: 3.0299. Min Act: -0.0000

Data Index: 350823 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.9992. Min Act: -0.0000

Data Index: 1003051 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.7169. Min Act: -0.0000

Data Index: 164155 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.8283. Min Act: -0.0000

Data Index: 1617777 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.6701. Min Act: -0.0000

Data Index: 1454805 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1470338 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.5695. Min Act: -0.0000

Data Index: 1539517 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.6999. Min Act: -0.0000

Data Index: 1615648 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.7167. Min Act: -0.0000

Data Index: 1573946 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.5237. Min Act: -0.0000

Data Index: 1392497 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.6432. Min Act: -0.0000

Data Index: 309753 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 5.1149. Min Range: -5.1149

Max Act: 2.7229. Min Act: -0.0000

Data Index: 716098 (C4 (Web Text))

Max Activating Token Index: 623