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

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

Neuron 590 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: 5.5683. Min Range: -5.5683

Max Act: 5.5683. Min Act: -0.1700

Data Index: 779570 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.4433. Min Act: -0.1699

Data Index: 151128 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.4433. Min Act: -0.1697

Data Index: 236081 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.3496. Min Act: -0.1700

Data Index: 819351 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.3183. Min Act: -0.1700

Data Index: 483144 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.2558. Min Act: -0.1700

Data Index: 879819 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.2246. Min Act: -0.1699

Data Index: 105404 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.1933. Min Act: -0.1700

Data Index: 1158765 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.1933. Min Act: -0.1700

Data Index: 747821 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.2246. Min Act: -0.1693

Data Index: 911495 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.1933. Min Act: -0.1700

Data Index: 599386 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.1308. Min Act: -0.1700

Data Index: 1317754 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.1308. Min Act: -0.1699

Data Index: 991776 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.1308. Min Act: -0.1700

Data Index: 612609 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.0996. Min Act: -0.1688

Data Index: 278005 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.0683. Min Act: -0.1700

Data Index: 991748 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.0683. Min Act: -0.1697

Data Index: 916531 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.0371. Min Act: -0.1700

Data Index: 1290390 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 5.5683. Min Range: -5.5683

Max Act: 5.0058. Min Act: -0.1700

Data Index: 96609 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 5.5683. Min Range: -5.5683

Max Act: 4.9746. Min Act: -0.1697

Data Index: 110213 (C4 (Web Text))

Max Activating Token Index: 954