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

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

Neuron 2136 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0002

Data Index: 32657 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1012. Min Act: -0.0002

Data Index: 584747 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1024. Min Act: -0.0002

Data Index: 579533 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0968. Min Act: -0.0002

Data Index: 437804 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0912. Min Act: -0.0002

Data Index: 524003 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0905. Min Act: -0.0002

Data Index: 377314 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0924. Min Act: -0.0002

Data Index: 174811 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1128568 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0851. Min Act: -0.0002

Data Index: 349463 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1262049 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0933. Min Act: -0.0002

Data Index: 923027 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1179144 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0801. Min Act: -0.0002

Data Index: 543748 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1079665 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0754. Min Act: -0.0002

Data Index: 753156 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1058485 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1330794 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0835. Min Act: -0.0002

Data Index: 675073 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0859. Min Act: -0.0002

Data Index: 23959 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1195853 (C4 (Web Text))

Max Activating Token Index: 217