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

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

Neuron 699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.3798. Min Act: -0.1700

Data Index: 972375 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.3170. Min Act: -0.1700

Data Index: 253507 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.1913. Min Act: -0.1700

Data Index: 43409 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.1440. Min Act: -0.1700

Data Index: 825124 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.1755. Min Act: -0.1700

Data Index: 156922 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.1283. Min Act: -0.1700

Data Index: 1270723 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0967. Min Act: -0.1700

Data Index: 937759 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.1283. Min Act: -0.1700

Data Index: 936529 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1008570 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0810. Min Act: -0.1700

Data Index: 921267 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0494. Min Act: -0.1700

Data Index: 1050453 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0810. Min Act: -0.1700

Data Index: 646177 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0652. Min Act: -0.1700

Data Index: 316191 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0494. Min Act: -0.1700

Data Index: 726213 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0652. Min Act: -0.1700

Data Index: 25957 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0336. Min Act: -0.1700

Data Index: 875089 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0178. Min Act: -0.1700

Data Index: 1300008 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0336. Min Act: -0.1700

Data Index: 826927 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0336. Min Act: -0.1700

Data Index: 808847 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 3.3798. Min Range: -3.3798

Max Act: 3.0178. Min Act: -0.1700

Data Index: 995535 (C4 (Web Text))

Max Activating Token Index: 985