Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.6204. Min Act: -0.1700

Data Index: 469856 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.4017. Min Act: -0.1700

Data Index: 1179353 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.4017. Min Act: -0.1700

Data Index: 158797 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2767. Min Act: -0.1700

Data Index: 1339024 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.3392. Min Act: -0.1700

Data Index: 941420 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2767. Min Act: -0.1700

Data Index: 350180 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2767. Min Act: -0.1700

Data Index: 484718 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2767. Min Act: -0.1700

Data Index: 529558 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2454. Min Act: -0.1700

Data Index: 131990 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2454. Min Act: -0.1700

Data Index: 609014 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2142. Min Act: -0.1700

Data Index: 1129566 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2142. Min Act: -0.1700

Data Index: 823510 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2454. Min Act: -0.1650

Data Index: 581624 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2142. Min Act: -0.1700

Data Index: 572861 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2142. Min Act: -0.1700

Data Index: 1129843 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2142. Min Act: -0.1700

Data Index: 1356484 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.2142. Min Act: -0.1700

Data Index: 19927 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.1829. Min Act: -0.1700

Data Index: 866734 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.1829. Min Act: -0.1700

Data Index: 1063028 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 5.6204. Min Range: -5.6204

Max Act: 5.1829. Min Act: -0.1700

Data Index: 1195136 (C4 (Web Text))

Max Activating Token Index: 971