Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1611 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.7695. Min Act: -0.0000

Data Index: 217589 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.7262. Min Act: -0.0000

Data Index: 304458 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.6727. Min Act: -0.0000

Data Index: 1012587 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.6104. Min Act: -0.0000

Data Index: 11322 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.3210. Min Act: -0.0000

Data Index: 170509 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.2019. Min Act: -0.0000

Data Index: 166414 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.1732. Min Act: -0.0000

Data Index: 877330 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.1263. Min Act: -0.0000

Data Index: 1148215 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.9889. Min Act: -0.0000

Data Index: 347656 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 2.7695. Min Range: -2.7695

Max Act: 2.2919. Min Act: -0.0000

Data Index: 559771 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.9954. Min Act: -0.0000

Data Index: 321006 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.9085. Min Act: -0.0000

Data Index: 668914 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.8960. Min Act: -0.0000

Data Index: 880807 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.8803. Min Act: -0.0000

Data Index: 741560 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.9391. Min Act: -0.0000

Data Index: 410077 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.8345. Min Act: -0.0000

Data Index: 1150076 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1315439 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.7502. Min Act: -0.0000

Data Index: 986633 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.6563. Min Act: -0.0000

Data Index: 309100 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 2.7695. Min Range: -2.7695

Max Act: 1.8058. Min Act: -0.0000

Data Index: 450643 (C4 (Web Text))

Max Activating Token Index: 995