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

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

Neuron 93 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.8627. Min Act: -0.1700

Data Index: 955489 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.8627. Min Act: -0.1700

Data Index: 976544 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.8314. Min Act: -0.1700

Data Index: 1291202 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.8002. Min Act: -0.1700

Data Index: 806027 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.8002. Min Act: -0.1700

Data Index: 566585 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7689. Min Act: -0.1700

Data Index: 942139 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7689. Min Act: -0.1700

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 427889 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1018409 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7219. Min Act: -0.1700

Data Index: 1122309 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.8002. Min Act: -0.1700

Data Index: 177486 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 905691 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 247564 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7219. Min Act: -0.1700

Data Index: 296789 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7219. Min Act: -0.1700

Data Index: 300624 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7689. Min Act: -0.1700

Data Index: 576934 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 686923 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 738295 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7376. Min Act: -0.1700

Data Index: 754942 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.8627. Min Range: -3.8627

Max Act: 3.7063. Min Act: -0.1700

Data Index: 785381 (C4 (Web Text))

Max Activating Token Index: 589