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

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

Neuron 1711 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: 3.4741. Min Range: -3.4741

Max Act: 3.4741. Min Act: -0.1700

Data Index: 852536 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.3015. Min Act: -0.1700

Data Index: 105749 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1915. Min Act: -0.1700

Data Index: 814238 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.2072. Min Act: -0.1700

Data Index: 848820 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.2387. Min Act: -0.1700

Data Index: 96978 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1757. Min Act: -0.1700

Data Index: 535873 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.2229. Min Act: -0.1700

Data Index: 334389 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1757. Min Act: -0.1700

Data Index: 218083 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1915. Min Act: -0.1700

Data Index: 971343 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1915. Min Act: -0.1700

Data Index: 908860 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1915. Min Act: -0.1700

Data Index: 774368 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1915. Min Act: -0.1700

Data Index: 408491 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1442. Min Act: -0.1700

Data Index: 440313 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1757. Min Act: -0.1700

Data Index: 692282 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1915. Min Act: -0.1700

Data Index: 741649 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1600. Min Act: -0.1700

Data Index: 342250 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1442. Min Act: -0.1700

Data Index: 409123 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1600. Min Act: -0.1700

Data Index: 864891 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1600. Min Act: -0.1700

Data Index: 620071 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 3.4741. Min Range: -3.4741

Max Act: 3.1285. Min Act: -0.1700

Data Index: 35115 (C4 (Web Text))

Max Activating Token Index: 495