Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1822 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1162. Min Act: -0.0004

Data Index: 512286 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1044. Min Act: -0.0004

Data Index: 1258531 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1007. Min Act: -0.0004

Data Index: 59752 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1040. Min Act: -0.0004

Data Index: 833206 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1057. Min Act: -0.0004

Data Index: 468962 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0964. Min Act: -0.0004

Data Index: 1104392 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0921. Min Act: -0.0004

Data Index: 1009819 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0910. Min Act: -0.0004

Data Index: 374024 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0983. Min Act: -0.0004

Data Index: 125880 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0938. Min Act: -0.0004

Data Index: 516040 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0932. Min Act: -0.0004

Data Index: 470544 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0934. Min Act: -0.0004

Data Index: 348302 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0916. Min Act: -0.0004

Data Index: 1058521 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1000. Min Act: -0.0004

Data Index: 991779 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0927. Min Act: -0.0004

Data Index: 1267674 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0999. Min Act: -0.0004

Data Index: 685226 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0789. Min Act: -0.0004

Data Index: 830648 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0932. Min Act: -0.0004

Data Index: 225081 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1003. Min Act: -0.0004

Data Index: 582712 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0920. Min Act: -0.0004

Data Index: 5827 (C4 (Web Text))

Max Activating Token Index: 333