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

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

Neuron 999 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: 3.5358. Min Range: -3.5358

Max Act: 3.5044. Min Act: -0.1700

Data Index: 645643 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.5358. Min Act: -0.1700

Data Index: 575077 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.5044. Min Act: -0.1700

Data Index: 1107444 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4417. Min Act: -0.1700

Data Index: 816626 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4417. Min Act: -0.1700

Data Index: 811427 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4417. Min Act: -0.1700

Data Index: 1093235 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4417. Min Act: -0.1700

Data Index: 37447 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3790. Min Act: -0.1700

Data Index: 867705 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4104. Min Act: -0.1700

Data Index: 575975 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1079302 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.4104. Min Act: -0.1700

Data Index: 95135 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3790. Min Act: -0.1700

Data Index: 151683 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3476. Min Act: -0.1700

Data Index: 1131286 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3790. Min Act: -0.1700

Data Index: 801651 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3790. Min Act: -0.1700

Data Index: 449716 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3790. Min Act: -0.1700

Data Index: 302417 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3790. Min Act: -0.1700

Data Index: 801996 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3476. Min Act: -0.1700

Data Index: 173498 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3476. Min Act: -0.1700

Data Index: 1091242 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.5358. Min Range: -3.5358

Max Act: 3.3476. Min Act: -0.1700

Data Index: 51695 (C4 (Web Text))

Max Activating Token Index: 12