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

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

Neuron 1891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0750. Min Range: -1.0750

Max Act: 1.0750. Min Act: -0.0001

Data Index: 1239288 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1250670 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6919. Min Act: -0.0001

Data Index: 337752 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6477. Min Act: -0.0001

Data Index: 1157939 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7509. Min Act: -0.0001

Data Index: 291031 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7105. Min Act: -0.0001

Data Index: 1407437 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7245. Min Act: -0.0001

Data Index: 1195308 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1144816 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7241. Min Act: -0.0001

Data Index: 608358 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6561. Min Act: -0.0001

Data Index: 98701 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6148. Min Act: -0.0001

Data Index: 725938 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6326. Min Act: -0.0001

Data Index: 1062238 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6005. Min Act: -0.0001

Data Index: 160096 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5696. Min Act: -0.0001

Data Index: 1166318 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1055641 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5807. Min Act: -0.0001

Data Index: 1322018 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5561. Min Act: -0.0001

Data Index: 1285232 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6348. Min Act: -0.0001

Data Index: 404148 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5585. Min Act: -0.0001

Data Index: 1136322 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6093. Min Act: -0.0001

Data Index: 577723 (C4 (Web Text))

Max Activating Token Index: 219