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

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

Neuron 298 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.8693. Min Act: -0.1700

Data Index: 976718 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.8693. Min Act: -0.1700

Data Index: 724402 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.7442. Min Act: -0.1700

Data Index: 876695 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.7755. Min Act: -0.1700

Data Index: 724795 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.7442. Min Act: -0.1700

Data Index: 1158768 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.7442. Min Act: -0.1700

Data Index: 353140 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.7442. Min Act: -0.1700

Data Index: 483407 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1017987 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.7129. Min Act: -0.1700

Data Index: 555437 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 274906 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1265314 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6503. Min Act: -0.1700

Data Index: 151164 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 848138 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 881609 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6503. Min Act: -0.1700

Data Index: 666442 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1005787 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6816. Min Act: -0.1700

Data Index: 199058 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6503. Min Act: -0.1700

Data Index: 1070095 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.8693. Min Range: -3.8693

Max Act: 3.6503. Min Act: -0.1700

Data Index: 150383 (C4 (Web Text))

Max Activating Token Index: 717