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

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

Neuron 102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0554. Min Range: -1.0554

Max Act: 1.0554. Min Act: -0.0000

Data Index: 946151 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9854. Min Act: -0.0000

Data Index: 348948 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.0554. Min Range: -1.0554

Max Act: 1.0074. Min Act: -0.0000

Data Index: 385562 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1102521 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1094033 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8736. Min Act: -0.0000

Data Index: 496052 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8736. Min Act: -0.0000

Data Index: 729454 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8433. Min Act: -0.0000

Data Index: 432546 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9174. Min Act: -0.0000

Data Index: 21601 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8254. Min Act: -0.0000

Data Index: 425604 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1314636 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8476. Min Act: -0.0000

Data Index: 723306 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1049724 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8227. Min Act: -0.0000

Data Index: 556579 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8279. Min Act: -0.0000

Data Index: 336779 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.7718. Min Act: -0.0000

Data Index: 47335 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.7760. Min Act: -0.0000

Data Index: 420430 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.7921. Min Act: -0.0000

Data Index: 848870 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1000383 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8040. Min Act: -0.0000

Data Index: 675229 (C4 (Web Text))

Max Activating Token Index: 964