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

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

Neuron 5202 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: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0002

Data Index: 474021 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1202781 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1325191 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1272 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1061298 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0886. Min Act: -0.0002

Data Index: 939135 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0860. Min Act: -0.0002

Data Index: 941396 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0830. Min Act: -0.0002

Data Index: 801530 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0816. Min Act: -0.0002

Data Index: 476555 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0826. Min Act: -0.0002

Data Index: 925557 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1561732 (Python Code)

Max Activating Token Index: 921

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0832. Min Act: -0.0002

Data Index: 410186 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0822. Min Act: -0.0002

Data Index: 602957 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1516125 (Python Code)

Max Activating Token Index: 722

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1440100 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1417204 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0809. Min Act: -0.0002

Data Index: 801481 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1155641 (C4 (Web Text))

Max Activating Token Index: 137