Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1530 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.6681. Min Act: -0.1700

Data Index: 379384 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.6396. Min Act: -0.1700

Data Index: 145241 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.6000. Min Act: -0.1700

Data Index: 446852 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.6107. Min Act: -0.1700

Data Index: 920175 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.6134. Min Act: -0.1700

Data Index: 492057 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5962. Min Act: -0.1700

Data Index: 739584 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5843. Min Act: -0.1700

Data Index: 1031198 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5767. Min Act: -0.1700

Data Index: 226222 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5758. Min Act: -0.1700

Data Index: 423864 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1066728 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5582. Min Act: -0.1700

Data Index: 150418 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5584. Min Act: -0.1700

Data Index: 932863 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5516. Min Act: -0.1700

Data Index: 1145888 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5302. Min Act: -0.1700

Data Index: 1416118 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5403. Min Act: -0.1700

Data Index: 1082800 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1038342 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5226. Min Act: -0.1700

Data Index: 717997 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5306. Min Act: -0.1700

Data Index: 604382 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.5312. Min Act: -0.1700

Data Index: 201089 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.6681. Min Range: -3.6681

Max Act: 3.4940. Min Act: -0.1700

Data Index: 258857 (C4 (Web Text))

Max Activating Token Index: 661