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

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

Neuron 215 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.6441. Min Act: -0.0000

Data Index: 158385 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1091156 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.3697. Min Act: -0.0000

Data Index: 914315 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.1870. Min Act: -0.0000

Data Index: 357146 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1129695 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.8097. Min Act: -0.0000

Data Index: 103265 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1199064 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.8390. Min Act: -0.0000

Data Index: 16056 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.6706. Min Act: -0.0000

Data Index: 70380 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.6769. Min Act: -0.0000

Data Index: 480868 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.6531. Min Act: -0.0000

Data Index: 914992 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1133827 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1346212 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1174612 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.5361. Min Act: -0.0000

Data Index: 677869 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.4794. Min Act: -0.0000

Data Index: 21672 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1577922 (Python Code)

Max Activating Token Index: 708

Text #17

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.4930. Min Act: -0.0000

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1300966 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.6441. Min Range: -1.6441

Max Act: 0.4695. Min Act: -0.0000

Data Index: 804111 (C4 (Web Text))

Max Activating Token Index: 60