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

Dataset: Open Web Text

Neuron 2160 in Layer 6

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: 4.6937. Min Range: -4.6937

Max Act: 4.6937. Min Act: -0.1700

Data Index: 5783528 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.5122. Min Act: -0.1700

Data Index: 4565861 (Open Web Text)

Max Activating Token Index: 879

Text #2

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.4928. Min Act: -0.1700

Data Index: 1504134 (Open Web Text)

Max Activating Token Index: 604

Text #3

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3770. Min Act: -0.1700

Data Index: 570116 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3822. Min Act: -0.1700

Data Index: 8150693 (Open Web Text)

Max Activating Token Index: 955

Text #5

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3699. Min Act: -0.1700

Data Index: 1708660 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3703. Min Act: -0.1700

Data Index: 4303062 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3716. Min Act: -0.1700

Data Index: 4802181 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3773. Min Act: -0.1700

Data Index: 5202782 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3293. Min Act: -0.1700

Data Index: 7855332 (Open Web Text)

Max Activating Token Index: 689

Text #10

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3167. Min Act: -0.1700

Data Index: 3880422 (Open Web Text)

Max Activating Token Index: 936

Text #11

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3332. Min Act: -0.1700

Data Index: 3770594 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3578. Min Act: -0.1700

Data Index: 426405 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3385. Min Act: -0.1700

Data Index: 4217565 (Open Web Text)

Max Activating Token Index: 825

Text #14

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3348. Min Act: -0.1700

Data Index: 4140294 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3130. Min Act: -0.1700

Data Index: 6720782 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3060. Min Act: -0.1700

Data Index: 5390539 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3053. Min Act: -0.1700

Data Index: 5116287 (Open Web Text)

Max Activating Token Index: 837

Text #18

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3152. Min Act: -0.1700

Data Index: 4858653 (Open Web Text)

Max Activating Token Index: 265

Text #19

Max Range: 4.6937. Min Range: -4.6937

Max Act: 4.3115. Min Act: -0.1700

Data Index: 1510197 (Open Web Text)

Max Activating Token Index: 586