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

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

Neuron 2718 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: 1.9052. Min Range: -1.9052

Max Act: 1.9052. Min Act: -0.0000

Data Index: 105780 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.5815. Min Act: -0.0000

Data Index: 391265 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.4805. Min Act: -0.0000

Data Index: 105222 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.5681. Min Act: -0.0000

Data Index: 409261 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.4928. Min Act: -0.0000

Data Index: 873257 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.4084. Min Act: -0.0000

Data Index: 556765 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1341410 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.3393. Min Act: -0.0000

Data Index: 246777 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2320. Min Act: -0.0000

Data Index: 279031 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.3125. Min Act: -0.0000

Data Index: 751456 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.3016. Min Act: -0.0000

Data Index: 306693 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2197. Min Act: -0.0000

Data Index: 662182 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2915. Min Act: -0.0000

Data Index: 890134 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2681. Min Act: -0.0000

Data Index: 820376 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2564. Min Act: -0.0000

Data Index: 989330 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2498. Min Act: -0.0000

Data Index: 415522 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2486. Min Act: -0.0000

Data Index: 959226 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.1659. Min Act: -0.0000

Data Index: 896464 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.2374. Min Act: -0.0000

Data Index: 618473 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.9052. Min Range: -1.9052

Max Act: 1.3987. Min Act: -0.0000

Data Index: 371422 (C4 (Web Text))

Max Activating Token Index: 990