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

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

Neuron 1868 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.8521. Min Act: -0.0000

Data Index: 486704 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.9573. Min Act: -0.0000

Data Index: 1038397 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.7369. Min Act: -0.0000

Data Index: 1277122 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.9772. Min Act: -0.0000

Data Index: 33271 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.4397. Min Act: -0.0000

Data Index: 1196683 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.5451. Min Act: -0.0000

Data Index: 666375 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.2622. Min Act: -0.0000

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.5114. Min Act: -0.0000

Data Index: 769766 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.4446. Min Act: -0.0000

Data Index: 396485 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.3285. Min Act: -0.0000

Data Index: 445469 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.3003. Min Act: -0.0000

Data Index: 920504 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.2720. Min Act: -0.0000

Data Index: 74713 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.1891. Min Act: -0.0000

Data Index: 346866 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.0480. Min Act: -0.0000

Data Index: 183529 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.2735. Min Act: -0.0000

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.0827. Min Act: -0.0000

Data Index: 244318 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.3092. Min Act: -0.0000

Data Index: 1100576 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1070026 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.2313. Min Act: -0.0000

Data Index: 972806 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 2.9772. Min Range: -2.9772

Max Act: 2.0120. Min Act: -0.0000

Data Index: 1213626 (C4 (Web Text))

Max Activating Token Index: 46