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

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

Neuron 1197 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: 3.0807. Min Range: -3.0807

Max Act: 3.0807. Min Act: -0.1700

Data Index: 324731 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1418005 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0758. Min Act: -0.1700

Data Index: 1367976 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0793. Min Act: -0.1700

Data Index: 733698 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0585. Min Act: -0.1700

Data Index: 806531 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0689. Min Act: -0.1700

Data Index: 490258 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1561991 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0029. Min Act: -0.1700

Data Index: 193790 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0019. Min Act: -0.1700

Data Index: 1401206 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1511197 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 3.0807. Min Range: -3.0807

Max Act: 3.0023. Min Act: -0.1700

Data Index: 1263933 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9962. Min Act: -0.1700

Data Index: 1432271 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9749. Min Act: -0.1700

Data Index: 654629 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9877. Min Act: -0.1700

Data Index: 198944 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9658. Min Act: -0.1700

Data Index: 1007497 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9515. Min Act: -0.1700

Data Index: 712575 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9622. Min Act: -0.1700

Data Index: 1057314 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9397. Min Act: -0.1700

Data Index: 1111075 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9452. Min Act: -0.1700

Data Index: 1387789 (Python Code)

Max Activating Token Index: 648

Text #19

Max Range: 3.0807. Min Range: -3.0807

Max Act: 2.9331. Min Act: -0.1700

Data Index: 1640554 (Python Code)

Max Activating Token Index: 269