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

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

Neuron 475 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: 3.7801. Min Range: -3.7801

Max Act: 3.7801. Min Act: -0.1700

Data Index: 598088 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.7488. Min Act: -0.1700

Data Index: 18227 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.3729. Min Act: -0.1700

Data Index: 1224125 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.3415. Min Act: -0.1700

Data Index: 286586 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.3572. Min Act: -0.1700

Data Index: 161534 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1135085 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.3101. Min Act: -0.1700

Data Index: 187395 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.3101. Min Act: -0.1700

Data Index: 392676 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2787. Min Act: -0.1700

Data Index: 461148 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2944. Min Act: -0.1700

Data Index: 32596 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2630. Min Act: -0.1700

Data Index: 42473 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.1844. Min Act: -0.1700

Data Index: 864885 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2630. Min Act: -0.1700

Data Index: 459469 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2473. Min Act: -0.1700

Data Index: 263873 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2473. Min Act: -0.1700

Data Index: 1310396 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2473. Min Act: -0.1700

Data Index: 822774 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2158. Min Act: -0.1700

Data Index: 214458 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2315. Min Act: -0.1700

Data Index: 155934 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2473. Min Act: -0.1700

Data Index: 266842 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 3.7801. Min Range: -3.7801

Max Act: 3.2630. Min Act: -0.1700

Data Index: 284358 (C4 (Web Text))

Max Activating Token Index: 17