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

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

Neuron 3122 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.4251. Min Act: -0.0000

Data Index: 510821 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.4947. Min Act: -0.0000

Data Index: 60942 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2986. Min Act: -0.0000

Data Index: 480219 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2801. Min Act: -0.0000

Data Index: 451972 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1822. Min Act: -0.0000

Data Index: 794947 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1056767 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1241375 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1669. Min Act: -0.0000

Data Index: 567011 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1201080 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.4947. Min Range: -1.4947

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1254943 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0807. Min Act: -0.0000

Data Index: 737753 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0500. Min Act: -0.0000

Data Index: 443017 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 1.4947. Min Range: -1.4947

Max Act: 0.9804. Min Act: -0.0000

Data Index: 594522 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.4947. Min Range: -1.4947

Max Act: 0.9728. Min Act: -0.0000

Data Index: 851673 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0180. Min Act: -0.0000

Data Index: 510119 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0196. Min Act: -0.0000

Data Index: 347397 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 1.4947. Min Range: -1.4947

Max Act: 0.9509. Min Act: -0.0000

Data Index: 911433 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0159. Min Act: -0.0000

Data Index: 587193 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0043. Min Act: -0.0000

Data Index: 228083 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.0497. Min Act: -0.0000

Data Index: 524076 (C4 (Web Text))

Max Activating Token Index: 711