Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1722 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4441. Min Range: -5.4441

Max Act: 5.4441. Min Act: -0.1700

Data Index: 59963 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.9753. Min Act: -0.1700

Data Index: 884446 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.9441. Min Act: -0.1700

Data Index: 1103805 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.9128. Min Act: -0.1700

Data Index: 729865 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 794408 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.9128. Min Act: -0.1700

Data Index: 137165 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 332644 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.9128. Min Act: -0.1700

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 352826 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8503. Min Act: -0.1700

Data Index: 822136 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8191. Min Act: -0.1700

Data Index: 189820 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 1249278 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 309966 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 262461 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8816. Min Act: -0.1700

Data Index: 397185 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.8191. Min Act: -0.1700

Data Index: 742728 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.7878. Min Act: -0.1700

Data Index: 686235 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.7878. Min Act: -0.1700

Data Index: 906681 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.7565. Min Act: -0.1700

Data Index: 1079247 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 5.4441. Min Range: -5.4441

Max Act: 4.7878. Min Act: -0.1700

Data Index: 1058455 (C4 (Web Text))

Max Activating Token Index: 644