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

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

Neuron 1142 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: 5.5484. Min Range: -5.5484

Max Act: 5.5484. Min Act: -0.1700

Data Index: 439835 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.5484. Min Act: -0.1700

Data Index: 1100524 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4859. Min Act: -0.1700

Data Index: 981932 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.5172. Min Act: -0.1698

Data Index: 586302 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.5172. Min Act: -0.1678

Data Index: 883864 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.5172. Min Act: -0.1693

Data Index: 364203 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4859. Min Act: -0.1691

Data Index: 365472 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4859. Min Act: -0.1700

Data Index: 885789 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4547. Min Act: -0.1700

Data Index: 769362 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4547. Min Act: -0.1700

Data Index: 566065 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4234. Min Act: -0.1700

Data Index: 1337785 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.3922. Min Act: -0.1700

Data Index: 183806 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4234. Min Act: -0.1700

Data Index: 650359 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4547. Min Act: -0.1698

Data Index: 1063609 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4234. Min Act: -0.1700

Data Index: 396371 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4547. Min Act: -0.1700

Data Index: 1195450 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4234. Min Act: -0.1700

Data Index: 1137789 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4234. Min Act: -0.1647

Data Index: 658570 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.3922. Min Act: -0.1700

Data Index: 214219 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 5.5484. Min Range: -5.5484

Max Act: 5.4234. Min Act: -0.1695

Data Index: 342773 (C4 (Web Text))

Max Activating Token Index: 645