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

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

Neuron 1593 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: 7.2132. Min Range: -7.2132

Max Act: 7.2132. Min Act: -0.1700

Data Index: 961369 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 7.2132. Min Range: -7.2132

Max Act: 7.1819. Min Act: -0.1700

Data Index: 521304 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 7.2132. Min Range: -7.2132

Max Act: 7.0569. Min Act: -0.1700

Data Index: 1134686 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.9944. Min Act: -0.1700

Data Index: 847980 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.9944. Min Act: -0.1700

Data Index: 105147 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.8694. Min Act: -0.1700

Data Index: 231104 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7444. Min Act: -0.1700

Data Index: 1076501 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.8069. Min Act: -0.1700

Data Index: 1279204 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7444. Min Act: -0.1700

Data Index: 288229 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7757. Min Act: -0.1700

Data Index: 1137260 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.8069. Min Act: -0.1700

Data Index: 662776 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7757. Min Act: -0.1700

Data Index: 1160393 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7444. Min Act: -0.1700

Data Index: 1214319 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7444. Min Act: -0.1700

Data Index: 418531 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7132. Min Act: -0.1700

Data Index: 505057 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.6507. Min Act: -0.1700

Data Index: 848831 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.7757. Min Act: -0.1700

Data Index: 166735 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.6507. Min Act: -0.1700

Data Index: 208434 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.6819. Min Act: -0.1700

Data Index: 952353 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 7.2132. Min Range: -7.2132

Max Act: 6.6819. Min Act: -0.1700

Data Index: 354482 (C4 (Web Text))

Max Activating Token Index: 680