Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 921 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0521. Min Range: -4.0521

Max Act: 4.0521. Min Act: -0.1700

Data Index: 321540 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 4.0521. Min Range: -4.0521

Max Act: 4.0337. Min Act: -0.1700

Data Index: 7370704 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.9903. Min Act: -0.1700

Data Index: 868607 (Open Web Text)

Max Activating Token Index: 452

Text #3

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.9799. Min Act: -0.1700

Data Index: 1759743 (Open Web Text)

Max Activating Token Index: 279

Text #4

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.9860. Min Act: -0.1700

Data Index: 2009338 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.8620. Min Act: -0.1700

Data Index: 5391657 (Open Web Text)

Max Activating Token Index: 880

Text #6

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.8292. Min Act: -0.1700

Data Index: 3527430 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.8595. Min Act: -0.1700

Data Index: 6316222 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.8218. Min Act: -0.1700

Data Index: 5431624 (Open Web Text)

Max Activating Token Index: 909

Text #9

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7936. Min Act: -0.1700

Data Index: 5035630 (Open Web Text)

Max Activating Token Index: 315

Text #10

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7943. Min Act: -0.1700

Data Index: 1091977 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.8404. Min Act: -0.1700

Data Index: 1070070 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7957. Min Act: -0.1700

Data Index: 465006 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.8231. Min Act: -0.1700

Data Index: 6240526 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7487. Min Act: -0.1700

Data Index: 4835530 (Open Web Text)

Max Activating Token Index: 205

Text #15

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7895. Min Act: -0.1700

Data Index: 1146848 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7830. Min Act: -0.1700

Data Index: 5917688 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7749. Min Act: -0.1700

Data Index: 3770583 (Open Web Text)

Max Activating Token Index: 529

Text #18

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7418. Min Act: -0.1700

Data Index: 1750942 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 4.0521. Min Range: -4.0521

Max Act: 3.7634. Min Act: -0.1700

Data Index: 5036561 (Open Web Text)

Max Activating Token Index: 419