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

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

Neuron 3466 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: 1.7708. Min Range: -1.7708

Max Act: 1.7708. Min Act: -0.0001

Data Index: 875298 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.6661. Min Act: -0.0001

Data Index: 1243893 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.5726. Min Act: -0.0001

Data Index: 274879 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.4850. Min Act: -0.0001

Data Index: 1298130 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.5760. Min Act: -0.0001

Data Index: 880603 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.4681. Min Act: -0.0001

Data Index: 588237 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.5290. Min Act: -0.0001

Data Index: 932758 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.4553. Min Act: -0.0001

Data Index: 719770 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.2604. Min Act: -0.0001

Data Index: 1091846 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.3327. Min Act: -0.0001

Data Index: 556681 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.2903. Min Act: -0.0001

Data Index: 199855 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.3244. Min Act: -0.0001

Data Index: 154724 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.3255. Min Act: -0.0001

Data Index: 1348693 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.3071. Min Act: -0.0001

Data Index: 192014 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.1895. Min Act: -0.0001

Data Index: 1174673 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.2809. Min Act: -0.0001

Data Index: 1155382 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.2813. Min Act: -0.0001

Data Index: 885366 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.2413. Min Act: -0.0001

Data Index: 1053363 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.3743. Min Act: -0.0001

Data Index: 465171 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 1.7708. Min Range: -1.7708

Max Act: 1.2246. Min Act: -0.0001

Data Index: 77981 (C4 (Web Text))

Max Activating Token Index: 462