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

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

Neuron 5138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1275311 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0898. Min Act: -0.0002

Data Index: 363950 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0885. Min Act: -0.0002

Data Index: 789259 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1462492 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1582074 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1570500 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1408533 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1620406 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0811. Min Act: -0.0002

Data Index: 48272 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1418685 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1382821 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1605036 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1361644 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1208179 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1274021 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0731. Min Act: -0.0002

Data Index: 203164 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0724. Min Act: -0.0002

Data Index: 716433 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0721. Min Act: -0.0002

Data Index: 910933 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0713. Min Act: -0.0002

Data Index: 515612 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1016320 (C4 (Web Text))

Max Activating Token Index: 16