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

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

Neuron 1026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1011784 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8438. Min Act: -0.0001

Data Index: 106499 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8174. Min Act: -0.0001

Data Index: 348677 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8105. Min Act: -0.0001

Data Index: 832495 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7739. Min Act: -0.0001

Data Index: 320611 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7648. Min Act: -0.0001

Data Index: 935992 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7403. Min Act: -0.0001

Data Index: 369463 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6938. Min Act: -0.0001

Data Index: 983712 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7379. Min Act: -0.0001

Data Index: 1034923 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7102. Min Act: -0.0001

Data Index: 697525 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5696. Min Act: -0.0001

Data Index: 635300 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7300. Min Act: -0.0001

Data Index: 138379 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7001. Min Act: -0.0001

Data Index: 1334945 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6580. Min Act: -0.0001

Data Index: 167257 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6833. Min Act: -0.0001

Data Index: 742749 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7005. Min Act: -0.0001

Data Index: 1069150 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6998. Min Act: -0.0001

Data Index: 903695 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7081. Min Act: -0.0001

Data Index: 1123844 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6670. Min Act: -0.0001

Data Index: 8385 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1174218 (C4 (Web Text))

Max Activating Token Index: 913