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

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

Neuron 1673 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: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 550863 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 1081454 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 818024 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 64940 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5433. Min Act: -0.1700

Data Index: 630233 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6371. Min Act: -0.1700

Data Index: 1146596 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 402850 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 837378 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5746. Min Act: -0.1700

Data Index: 1205581 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 1014101 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6683. Min Act: -0.1700

Data Index: 732741 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6058. Min Act: -0.1700

Data Index: 423471 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5121. Min Act: -0.1700

Data Index: 437036 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5433. Min Act: -0.1700

Data Index: 227961 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5746. Min Act: -0.1700

Data Index: 1008870 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5433. Min Act: -0.1700

Data Index: 562255 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4808. Min Act: -0.1700

Data Index: 332896 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5433. Min Act: -0.1700

Data Index: 703475 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4808. Min Act: -0.1700

Data Index: 444430 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5433. Min Act: -0.1700

Data Index: 451114 (C4 (Web Text))

Max Activating Token Index: 604