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

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

Neuron 2561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0921. Min Range: -1.0921

Max Act: 1.0921. Min Act: -0.0000

Data Index: 134283 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9645. Min Act: -0.0000

Data Index: 98237 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1077831 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9235. Min Act: -0.0000

Data Index: 747543 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8899. Min Act: -0.0000

Data Index: 858056 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1006488 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9052. Min Act: -0.0000

Data Index: 936011 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.7612. Min Act: -0.0000

Data Index: 465827 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8731. Min Act: -0.0000

Data Index: 542710 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8269. Min Act: -0.0000

Data Index: 888220 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9038. Min Act: -0.0000

Data Index: 498218 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8589. Min Act: -0.0000

Data Index: 873730 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8056. Min Act: -0.0000

Data Index: 114552 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1101573 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8254. Min Act: -0.0000

Data Index: 348708 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8909. Min Act: -0.0000

Data Index: 607228 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1133965 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8363. Min Act: -0.0000

Data Index: 380551 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.7879. Min Act: -0.0000

Data Index: 599682 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8148. Min Act: -0.0000

Data Index: 106709 (C4 (Web Text))

Max Activating Token Index: 189