Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 811 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.4123. Min Act: -0.1700

Data Index: 816688 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.4280. Min Act: -0.1700

Data Index: 619711 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3966. Min Act: -0.1700

Data Index: 443955 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3338. Min Act: -0.1700

Data Index: 1785 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3338. Min Act: -0.1700

Data Index: 808576 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3181. Min Act: -0.1700

Data Index: 401192 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3024. Min Act: -0.1700

Data Index: 201502 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2867. Min Act: -0.1700

Data Index: 332779 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2710. Min Act: -0.1700

Data Index: 1148846 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2710. Min Act: -0.1700

Data Index: 595319 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 873666 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2710. Min Act: -0.1700

Data Index: 1274625 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 1254196 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 748195 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 1211537 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 874912 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1039512 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 366710 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2553. Min Act: -0.1700

Data Index: 980056 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2396. Min Act: -0.1700

Data Index: 376445 (C4 (Web Text))

Max Activating Token Index: 670