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

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

Neuron 1777 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9745. Min Act: -0.0003

Data Index: 19690 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8645. Min Act: -0.0002

Data Index: 33992 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8687. Min Act: -0.0002

Data Index: 33930 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8577. Min Act: -0.0002

Data Index: 1125613 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8381. Min Act: -0.0003

Data Index: 60244 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8487. Min Act: -0.0002

Data Index: 466674 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8281. Min Act: -0.0002

Data Index: 340258 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8079. Min Act: -0.0002

Data Index: 745822 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8052. Min Act: -0.0002

Data Index: 185686 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8104. Min Act: -0.0002

Data Index: 691119 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7943. Min Act: -0.0002

Data Index: 339087 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7984. Min Act: -0.0002

Data Index: 397221 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7921. Min Act: -0.0002

Data Index: 604964 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7761. Min Act: -0.0002

Data Index: 1258158 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7783. Min Act: -0.0003

Data Index: 98354 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7863. Min Act: -0.0002

Data Index: 326473 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7877. Min Act: -0.0002

Data Index: 1262276 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7815. Min Act: -0.0002

Data Index: 889468 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7662. Min Act: -0.0003

Data Index: 52986 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7840. Min Act: -0.0002

Data Index: 1277407 (C4 (Web Text))

Max Activating Token Index: 14