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

Dataset: Open Web Text

Neuron 2663 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: 5.5438. Min Range: -5.5438

Max Act: 5.5438. Min Act: -0.1700

Data Index: 7117216 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.4366. Min Act: -0.1700

Data Index: 7747738 (Open Web Text)

Max Activating Token Index: 797

Text #2

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.4217. Min Act: -0.1700

Data Index: 5943554 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3611. Min Act: -0.1700

Data Index: 6669757 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.4155. Min Act: -0.1700

Data Index: 5438867 (Open Web Text)

Max Activating Token Index: 616

Text #5

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.4490. Min Act: -0.1700

Data Index: 3703805 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.4076. Min Act: -0.1700

Data Index: 7732175 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3135. Min Act: -0.1700

Data Index: 4177320 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3250. Min Act: -0.1700

Data Index: 8818992 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3224. Min Act: -0.1700

Data Index: 5778773 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3025. Min Act: -0.1700

Data Index: 4668974 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2921. Min Act: -0.1700

Data Index: 4500842 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3053. Min Act: -0.1700

Data Index: 8890 (Open Web Text)

Max Activating Token Index: 283

Text #13

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2768. Min Act: -0.1700

Data Index: 4615481 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.3296. Min Act: -0.1700

Data Index: 4304760 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2521. Min Act: -0.1700

Data Index: 1094682 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2978. Min Act: -0.1700

Data Index: 5696204 (Open Web Text)

Max Activating Token Index: 572

Text #17

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2842. Min Act: -0.1700

Data Index: 7040424 (Open Web Text)

Max Activating Token Index: 325

Text #18

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2641. Min Act: -0.1700

Data Index: 4101315 (Open Web Text)

Max Activating Token Index: 600

Text #19

Max Range: 5.5438. Min Range: -5.5438

Max Act: 5.2597. Min Act: -0.1700

Data Index: 4136684 (Open Web Text)

Max Activating Token Index: 277