Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.8048. Min Act: -0.0000

Data Index: 539565 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.8201. Min Act: -0.0001

Data Index: 195623 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6989. Min Act: -0.0001

Data Index: 734972 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6934. Min Act: -0.0001

Data Index: 1291538 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6750. Min Act: -0.0000

Data Index: 466769 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6745. Min Act: -0.0000

Data Index: 657576 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1221153 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6443. Min Act: -0.0001

Data Index: 734606 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6788. Min Act: -0.0000

Data Index: 588466 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.6402. Min Act: -0.0001

Data Index: 1176472 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1021390 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1044755 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5403. Min Act: -0.0001

Data Index: 311012 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5675. Min Act: -0.0000

Data Index: 328672 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5048. Min Act: -0.0000

Data Index: 989670 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5584. Min Act: -0.0001

Data Index: 434529 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5121. Min Act: -0.0000

Data Index: 57668 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1325787 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1024340 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.8201. Min Range: -0.8201

Max Act: 0.5238. Min Act: -0.0000

Data Index: 798426 (C4 (Web Text))

Max Activating Token Index: 684