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

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

Neuron 3820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0000

Data Index: 361489 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1041. Min Act: -0.0000

Data Index: 122591 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1117. Min Act: -0.0000

Data Index: 643587 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1072884 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0938. Min Act: -0.0000

Data Index: 639051 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0924. Min Act: -0.0000

Data Index: 67801 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1276771 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1279217 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0858. Min Act: -0.0000

Data Index: 733229 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0845. Min Act: -0.0000

Data Index: 655561 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0781. Min Act: -0.0000

Data Index: 328799 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0864. Min Act: -0.0000

Data Index: 7273 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1052520 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0789. Min Act: -0.0000

Data Index: 457994 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0789. Min Act: -0.0000

Data Index: 626841 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1554966 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0811. Min Act: -0.0000

Data Index: 41664 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0753. Min Act: -0.0000

Data Index: 522445 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0863. Min Act: -0.0000

Data Index: 676661 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1076767 (C4 (Web Text))

Max Activating Token Index: 569