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

Dataset: Open Web Text

Neuron 1635 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: 3.0182. Min Range: -3.0182

Max Act: 3.0182. Min Act: -0.1700

Data Index: 6976158 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.9986. Min Act: -0.1700

Data Index: 3073184 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.9624. Min Act: -0.1700

Data Index: 2677353 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.9816. Min Act: -0.1700

Data Index: 2181355 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.9228. Min Act: -0.1700

Data Index: 8232808 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.9170. Min Act: -0.1700

Data Index: 7016479 (Open Web Text)

Max Activating Token Index: 298

Text #6

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.9161. Min Act: -0.1700

Data Index: 987127 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8932. Min Act: -0.1700

Data Index: 7022957 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8762. Min Act: -0.1700

Data Index: 5442737 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8752. Min Act: -0.1700

Data Index: 4008116 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8832. Min Act: -0.1700

Data Index: 4551556 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8687. Min Act: -0.1700

Data Index: 6267261 (Open Web Text)

Max Activating Token Index: 294

Text #12

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8927. Min Act: -0.1700

Data Index: 1504610 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8753. Min Act: -0.1700

Data Index: 4550750 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8434. Min Act: -0.1700

Data Index: 7439787 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8440. Min Act: -0.1700

Data Index: 5994538 (Open Web Text)

Max Activating Token Index: 822

Text #16

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8621. Min Act: -0.1700

Data Index: 4543237 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8443. Min Act: -0.1700

Data Index: 7388331 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8358. Min Act: -0.1700

Data Index: 406379 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8280. Min Act: -0.1700

Data Index: 6742898 (Open Web Text)

Max Activating Token Index: 558