Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.7377. Min Act: -0.1700

Data Index: 1325435 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.5502. Min Act: -0.1700

Data Index: 1356866 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.5502. Min Act: -0.1700

Data Index: 1322794 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4877. Min Act: -0.1700

Data Index: 977840 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4252. Min Act: -0.1700

Data Index: 163134 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4565. Min Act: -0.1700

Data Index: 486912 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4252. Min Act: -0.1700

Data Index: 250777 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3940. Min Act: -0.1700

Data Index: 722344 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4252. Min Act: -0.1699

Data Index: 1128512 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4565. Min Act: -0.1700

Data Index: 988911 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.4877. Min Act: -0.1700

Data Index: 194917 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3940. Min Act: -0.1700

Data Index: 337867 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3627. Min Act: -0.1700

Data Index: 1057175 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3627. Min Act: -0.1700

Data Index: 211430 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.2690. Min Act: -0.1700

Data Index: 565746 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3315. Min Act: -0.1700

Data Index: 485996 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.2377. Min Act: -0.1700

Data Index: 1034967 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3002. Min Act: -0.1700

Data Index: 166416 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3002. Min Act: -0.1700

Data Index: 1266856 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 5.7377. Min Range: -5.7377

Max Act: 5.3940. Min Act: -0.1700

Data Index: 278429 (C4 (Web Text))

Max Activating Token Index: 787