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

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

Neuron 378 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: 5.6256. Min Range: -5.6256

Max Act: 5.6256. Min Act: -0.1700

Data Index: 1173368 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.5631. Min Act: -0.1700

Data Index: 37501 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.4381. Min Act: -0.1700

Data Index: 1249528 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.3131. Min Act: -0.1700

Data Index: 1024818 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.3443. Min Act: -0.1700

Data Index: 1023423 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.1881. Min Act: -0.1700

Data Index: 1213831 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.2506. Min Act: -0.1700

Data Index: 1225461 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.1568. Min Act: -0.1700

Data Index: 294849 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.1881. Min Act: -0.1700

Data Index: 1048539 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0631. Min Act: -0.1700

Data Index: 964982 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0631. Min Act: -0.1698

Data Index: 580952 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.1256. Min Act: -0.1700

Data Index: 285055 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0318. Min Act: -0.1700

Data Index: 851265 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0318. Min Act: -0.1700

Data Index: 542860 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0631. Min Act: -0.1700

Data Index: 1285762 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0631. Min Act: -0.1700

Data Index: 486078 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0318. Min Act: -0.1700

Data Index: 1340195 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0631. Min Act: -0.1700

Data Index: 292175 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0006. Min Act: -0.1700

Data Index: 36599 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 5.6256. Min Range: -5.6256

Max Act: 5.0006. Min Act: -0.1700

Data Index: 200782 (C4 (Web Text))

Max Activating Token Index: 187