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

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

Neuron 623 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: 5.7678. Min Range: -5.7678

Max Act: 5.7678. Min Act: -0.1700

Data Index: 266127 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.7365. Min Act: -0.1700

Data Index: 352997 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.7678. Min Act: -0.1700

Data Index: 916297 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.7053. Min Act: -0.1700

Data Index: 665331 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.5490. Min Act: -0.1700

Data Index: 795591 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6740. Min Act: -0.1700

Data Index: 432444 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1234984 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6428. Min Act: -0.1700

Data Index: 188964 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6115. Min Act: -0.1700

Data Index: 263723 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.5803. Min Act: -0.1700

Data Index: 359827 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6428. Min Act: -0.1700

Data Index: 251757 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6428. Min Act: -0.1700

Data Index: 78234 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.5803. Min Act: -0.1700

Data Index: 226290 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6115. Min Act: -0.1700

Data Index: 898274 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6115. Min Act: -0.1700

Data Index: 685123 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.4553. Min Act: -0.1700

Data Index: 635304 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1015598 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.5178. Min Act: -0.1700

Data Index: 321444 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.4240. Min Act: -0.1700

Data Index: 97910 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 5.7678. Min Range: -5.7678

Max Act: 5.6115. Min Act: -0.1700

Data Index: 651033 (C4 (Web Text))

Max Activating Token Index: 388