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

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

Neuron 3337 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: 4.5468. Min Range: -4.5468

Max Act: 4.5085. Min Act: -0.0000

Data Index: 1215880 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.5405. Min Act: -0.0000

Data Index: 527821 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.5468. Min Act: -0.0000

Data Index: 173010 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.5373. Min Act: -0.0000

Data Index: 220510 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.5346. Min Act: -0.0000

Data Index: 583879 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.5100. Min Act: -0.0000

Data Index: 592264 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.2251. Min Act: -0.0000

Data Index: 862531 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.3251. Min Act: -0.0000

Data Index: 1093214 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.1490. Min Act: -0.0000

Data Index: 799757 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.2732. Min Act: -0.0000

Data Index: 156207 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.0577. Min Act: -0.0000

Data Index: 306854 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.2531. Min Act: -0.0000

Data Index: 769950 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.2004. Min Act: -0.0000

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.0276. Min Act: -0.0000

Data Index: 237122 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.1839. Min Act: -0.0000

Data Index: 1046920 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.1119. Min Act: -0.0000

Data Index: 729147 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.1006. Min Act: -0.0000

Data Index: 414556 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.0565. Min Act: -0.0000

Data Index: 537977 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 4.5468. Min Range: -4.5468

Max Act: 3.9036. Min Act: -0.0000

Data Index: 211163 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 4.5468. Min Range: -4.5468

Max Act: 4.0310. Min Act: -0.0000

Data Index: 640054 (C4 (Web Text))

Max Activating Token Index: 600