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

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

Neuron 918 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.6710. Min Act: -0.1700

Data Index: 316570 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4835. Min Act: -0.1700

Data Index: 433005 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4210. Min Act: -0.1700

Data Index: 134348 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4835. Min Act: -0.1700

Data Index: 306868 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4835. Min Act: -0.1700

Data Index: 894502 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4523. Min Act: -0.1699

Data Index: 1032584 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4210. Min Act: -0.1700

Data Index: 755065 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.4210. Min Act: -0.1700

Data Index: 349536 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.3273. Min Act: -0.1700

Data Index: 851321 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.3273. Min Act: -0.1700

Data Index: 290006 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.3898. Min Act: -0.1700

Data Index: 735524 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.3585. Min Act: -0.1700

Data Index: 556762 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.2960. Min Act: -0.1700

Data Index: 1149932 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.3273. Min Act: -0.1700

Data Index: 703764 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.2648. Min Act: -0.1700

Data Index: 475267 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.2648. Min Act: -0.1700

Data Index: 879882 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.2335. Min Act: -0.1700

Data Index: 94355 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.2335. Min Act: -0.1700

Data Index: 494272 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.1398. Min Act: -0.1700

Data Index: 260530 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 5.6710. Min Range: -5.6710

Max Act: 5.1710. Min Act: -0.1700

Data Index: 505930 (C4 (Web Text))

Max Activating Token Index: 625