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

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

Neuron 5085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.5617. Min Act: -0.0002

Data Index: 1246612 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.8504. Min Act: -0.0002

Data Index: 1134303 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.6584. Min Act: -0.0002

Data Index: 854661 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.3680. Min Act: -0.0002

Data Index: 1310336 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.1972. Min Act: -0.0002

Data Index: 45607 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.3365. Min Act: -0.0002

Data Index: 769731 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.9187. Min Act: -0.0003

Data Index: 484963 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.1390. Min Act: -0.0002

Data Index: 923995 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.0396. Min Act: -0.0002

Data Index: 1143523 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.6453. Min Act: -0.0002

Data Index: 591369 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.9230. Min Act: -0.0002

Data Index: 1106585 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.0106. Min Act: -0.0002

Data Index: 1348669 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.0070. Min Act: -0.0002

Data Index: 1154788 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.8634. Min Act: -0.0002

Data Index: 310363 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.0252. Min Act: -0.0002

Data Index: 521438 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.1195. Min Act: -0.0002

Data Index: 843124 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.9392. Min Act: -0.0002

Data Index: 1175308 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.8698. Min Act: -0.0002

Data Index: 1149296 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 3.5617. Min Range: -3.5617

Max Act: 1.8179. Min Act: -0.0002

Data Index: 737225 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 3.5617. Min Range: -3.5617

Max Act: 2.0315. Min Act: -0.0002

Data Index: 54120 (C4 (Web Text))

Max Activating Token Index: 147