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

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

Neuron 305 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.4400. Min Act: -0.0002

Data Index: 522118 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2346. Min Act: -0.0002

Data Index: 1127481 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2679. Min Act: -0.0001

Data Index: 1251120 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2281. Min Act: -0.0001

Data Index: 68869 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2036. Min Act: -0.0002

Data Index: 1276017 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1936. Min Act: -0.0001

Data Index: 1009712 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2209. Min Act: -0.0001

Data Index: 338494 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1113. Min Act: -0.0002

Data Index: 1029153 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0725. Min Act: -0.0002

Data Index: 1265175 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0826. Min Act: -0.0001

Data Index: 789815 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1014. Min Act: -0.0002

Data Index: 969015 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1124. Min Act: -0.0002

Data Index: 909441 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0925. Min Act: -0.0001

Data Index: 375657 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0808. Min Act: -0.0001

Data Index: 326704 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0556. Min Act: -0.0001

Data Index: 1525503 (Python Code)

Max Activating Token Index: 918

Text #15

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1346. Min Act: -0.0002

Data Index: 64910 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.4400. Min Range: -1.4400

Max Act: 0.9635. Min Act: -0.0002

Data Index: 944423 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0242. Min Act: -0.0001

Data Index: 1063490 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0609. Min Act: -0.0002

Data Index: 470893 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0707. Min Act: -0.0001

Data Index: 1111019 (C4 (Web Text))

Max Activating Token Index: 17