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

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

Neuron 929 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: 8.1531. Min Range: -8.1531

Max Act: 8.1531. Min Act: -0.1700

Data Index: 1084840 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 8.1531. Min Range: -8.1531

Max Act: 8.1531. Min Act: -0.1700

Data Index: 1198637 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 8.1531. Min Range: -8.1531

Max Act: 8.0906. Min Act: -0.1700

Data Index: 626823 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 8.1531. Min Range: -8.1531

Max Act: 8.0281. Min Act: -0.1700

Data Index: 1282467 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.8406. Min Act: -0.1700

Data Index: 85541 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.7781. Min Act: -0.1700

Data Index: 453548 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.7156. Min Act: -0.1700

Data Index: 750398 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.7781. Min Act: -0.1700

Data Index: 252843 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.7156. Min Act: -0.1700

Data Index: 1338079 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5281. Min Act: -0.1700

Data Index: 1071137 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.6531. Min Act: -0.1700

Data Index: 1200365 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.6531. Min Act: -0.1700

Data Index: 50931 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5906. Min Act: -0.1700

Data Index: 1045000 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5906. Min Act: -0.1700

Data Index: 736221 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5906. Min Act: -0.1700

Data Index: 1200280 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5906. Min Act: -0.1700

Data Index: 178825 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5906. Min Act: -0.1700

Data Index: 257153 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5906. Min Act: -0.1700

Data Index: 917621 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.4968. Min Act: -0.1700

Data Index: 96934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 8.1531. Min Range: -8.1531

Max Act: 7.5281. Min Act: -0.1700

Data Index: 603478 (C4 (Web Text))

Max Activating Token Index: 605