Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1863 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8328. Min Range: -2.8328

Max Act: 2.8328. Min Act: -0.0000

Data Index: 770505 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.9687. Min Act: -0.0000

Data Index: 703147 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.7763. Min Act: -0.0000

Data Index: 658737 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.7101. Min Act: -0.0000

Data Index: 484694 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.6985. Min Act: -0.0000

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5722. Min Act: -0.0000

Data Index: 571144 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5710. Min Act: -0.0000

Data Index: 393708 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.7176. Min Act: -0.0000

Data Index: 906106 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5108. Min Act: 0.0000

Data Index: 1014366 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5878. Min Act: -0.0000

Data Index: 545960 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5684. Min Act: -0.0000

Data Index: 896256 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1330396 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5400. Min Act: -0.0000

Data Index: 1172619 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1159468 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.6439. Min Act: -0.0000

Data Index: 287694 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5688. Min Act: -0.0000

Data Index: 334950 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1086604 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5613. Min Act: -0.0000

Data Index: 314307 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.5568. Min Act: -0.0000

Data Index: 675649 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.8328. Min Range: -2.8328

Max Act: 1.4714. Min Act: -0.0000

Data Index: 577218 (C4 (Web Text))

Max Activating Token Index: 773