Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 418 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.5182. Min Act: -0.1700

Data Index: 43744 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.4326. Min Act: -0.1700

Data Index: 1195204 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.4319. Min Act: -0.1700

Data Index: 1234280 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3844. Min Act: -0.1700

Data Index: 439457 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3921. Min Act: -0.1700

Data Index: 956392 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3623. Min Act: -0.1699

Data Index: 1229836 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3812. Min Act: -0.1700

Data Index: 83879 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3519. Min Act: -0.1700

Data Index: 57768 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3586. Min Act: -0.1700

Data Index: 1146024 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.3012. Min Act: -0.1700

Data Index: 465934 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.2842. Min Act: -0.1700

Data Index: 237120 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.2685. Min Act: -0.1700

Data Index: 1552287 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.2443. Min Act: -0.1699

Data Index: 302662 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.2637. Min Act: -0.1700

Data Index: 1435505 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.2387. Min Act: -0.1699

Data Index: 997822 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.2038. Min Act: -0.1682

Data Index: 1350362 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.1652. Min Act: -0.1693

Data Index: 1347636 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.1802. Min Act: -0.1700

Data Index: 1307306 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.1977. Min Act: -0.1700

Data Index: 325773 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 4.5182. Min Range: -4.5182

Max Act: 4.1374. Min Act: -0.1700

Data Index: 793110 (C4 (Web Text))

Max Activating Token Index: 171