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

Dataset: Open Web Text

Neuron 2522 in Layer 3

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: 4.9185. Min Range: -4.9185

Max Act: 4.9185. Min Act: -0.1700

Data Index: 4395340 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.8753. Min Act: -0.1700

Data Index: 2804007 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.8088. Min Act: -0.1700

Data Index: 2386693 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.8244. Min Act: -0.1700

Data Index: 5856774 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.8067. Min Act: -0.1700

Data Index: 415566 (Open Web Text)

Max Activating Token Index: 204

Text #5

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.8055. Min Act: -0.1700

Data Index: 462920 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7370. Min Act: -0.1700

Data Index: 2497649 (Open Web Text)

Max Activating Token Index: 716

Text #7

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7822. Min Act: -0.1700

Data Index: 2371650 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7500. Min Act: -0.1700

Data Index: 2645472 (Open Web Text)

Max Activating Token Index: 491

Text #9

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7533. Min Act: -0.1700

Data Index: 3762099 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7377. Min Act: -0.1700

Data Index: 8542001 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7508. Min Act: -0.1700

Data Index: 8406348 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7666. Min Act: -0.1700

Data Index: 6833485 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7112. Min Act: -0.1700

Data Index: 1248092 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7392. Min Act: -0.1700

Data Index: 4051307 (Open Web Text)

Max Activating Token Index: 243

Text #15

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7060. Min Act: -0.1700

Data Index: 5457246 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7437. Min Act: -0.1700

Data Index: 567732 (Open Web Text)

Max Activating Token Index: 766

Text #17

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7255. Min Act: -0.1700

Data Index: 1837817 (Open Web Text)

Max Activating Token Index: 404

Text #18

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7165. Min Act: -0.1700

Data Index: 1844222 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 4.9185. Min Range: -4.9185

Max Act: 4.7171. Min Act: -0.1700

Data Index: 2437588 (Open Web Text)

Max Activating Token Index: 870