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

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

Neuron 1660 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: 8.0999. Min Range: -8.0999

Max Act: 8.0999. Min Act: -0.1700

Data Index: 536700 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.9124. Min Act: -0.1700

Data Index: 735153 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.7874. Min Act: -0.1700

Data Index: 871278 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.6624. Min Act: -0.1700

Data Index: 551725 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5999. Min Act: -0.1700

Data Index: 402808 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.6624. Min Act: -0.1700

Data Index: 119625 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.4749. Min Act: -0.1700

Data Index: 1165206 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.6624. Min Act: -0.1700

Data Index: 237652 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.6624. Min Act: -0.1700

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5374. Min Act: -0.1700

Data Index: 283494 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5374. Min Act: -0.1700

Data Index: 638700 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5374. Min Act: -0.1700

Data Index: 195179 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5374. Min Act: -0.1700

Data Index: 501476 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.4124. Min Act: -0.1700

Data Index: 421678 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.6624. Min Act: -0.1700

Data Index: 1261676 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.6624. Min Act: -0.1700

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5374. Min Act: -0.1700

Data Index: 75723 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.5999. Min Act: -0.1700

Data Index: 1099161 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.4124. Min Act: -0.1700

Data Index: 687435 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 8.0999. Min Range: -8.0999

Max Act: 7.4124. Min Act: -0.1700

Data Index: 528685 (C4 (Web Text))

Max Activating Token Index: 24