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

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

Neuron 3719 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: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0002

Data Index: 717679 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0923. Min Act: -0.0002

Data Index: 530405 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1026723 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0924. Min Act: -0.0002

Data Index: 623035 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0908. Min Act: -0.0002

Data Index: 792871 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0901. Min Act: -0.0002

Data Index: 957247 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1041481 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0873. Min Act: -0.0002

Data Index: 78621 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0862. Min Act: -0.0002

Data Index: 926367 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0862. Min Act: -0.0002

Data Index: 658546 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1273113 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1039164 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0859. Min Act: -0.0002

Data Index: 358310 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1291780 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0829. Min Act: -0.0002

Data Index: 169232 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1233312 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1303551 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0793. Min Act: -0.0002

Data Index: 919014 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0821. Min Act: -0.0002

Data Index: 400863 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0789. Min Act: -0.0002

Data Index: 91799 (C4 (Web Text))

Max Activating Token Index: 522