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

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

Neuron 1016 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1029073 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.6555. Min Act: -0.0000

Data Index: 770386 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.4690. Min Act: -0.0000

Data Index: 483335 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1433016 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1515606 (Python Code)

Max Activating Token Index: 769

Text #5

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.4353. Min Act: -0.0000

Data Index: 110487 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3988. Min Act: -0.0000

Data Index: 814868 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3903. Min Act: -0.0000

Data Index: 818650 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3680. Min Act: -0.0000

Data Index: 599494 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3988. Min Act: -0.0000

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1372819 (Python Code)

Max Activating Token Index: 414

Text #11

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1146985 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3649. Min Act: -0.0000

Data Index: 723646 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3738. Min Act: -0.0000

Data Index: 475227 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3872. Min Act: -0.0000

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1415601 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3643. Min Act: -0.0000

Data Index: 898981 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3722. Min Act: -0.0000

Data Index: 493253 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3484. Min Act: -0.0000

Data Index: 468497 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.6555. Min Range: -0.6555

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1090425 (C4 (Web Text))

Max Activating Token Index: 80