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

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

Neuron 5077 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2815. Min Range: -2.2815

Max Act: 2.2815. Min Act: -0.0000

Data Index: 70824 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5493. Min Act: -0.0000

Data Index: 200690 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.6243. Min Act: -0.0000

Data Index: 41547 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5729. Min Act: -0.0000

Data Index: 636548 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5222. Min Act: -0.0000

Data Index: 266681 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5446. Min Act: -0.0000

Data Index: 908514 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1216577 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5384. Min Act: -0.0000

Data Index: 131757 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.5988. Min Act: -0.0000

Data Index: 495666 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.4616. Min Act: -0.0000

Data Index: 130954 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.4363. Min Act: -0.0000

Data Index: 1083826 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.4242. Min Act: -0.0000

Data Index: 669604 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.3718. Min Act: -0.0000

Data Index: 687449 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.3870. Min Act: -0.0000

Data Index: 381938 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.4130. Min Act: -0.0000

Data Index: 3378 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.4389. Min Act: -0.0000

Data Index: 128109 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.3960. Min Act: -0.0000

Data Index: 644222 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.3224. Min Act: -0.0000

Data Index: 129109 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.3207. Min Act: -0.0000

Data Index: 387924 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 2.2815. Min Range: -2.2815

Max Act: 1.2265. Min Act: -0.0000

Data Index: 123036 (C4 (Web Text))

Max Activating Token Index: 135