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

Dataset: Open Web Text

Neuron 2378 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: 5.4077. Min Range: -5.4077

Max Act: 5.4077. Min Act: -0.1700

Data Index: 1687452 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.3022. Min Act: -0.1700

Data Index: 662378 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.2157. Min Act: -0.1700

Data Index: 3951391 (Open Web Text)

Max Activating Token Index: 644

Text #3

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.1363. Min Act: -0.1700

Data Index: 6678637 (Open Web Text)

Max Activating Token Index: 746

Text #4

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.0837. Min Act: -0.1700

Data Index: 3099370 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.0685. Min Act: -0.1700

Data Index: 7702168 (Open Web Text)

Max Activating Token Index: 225

Text #6

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.0573. Min Act: -0.1700

Data Index: 5412265 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.0705. Min Act: -0.1700

Data Index: 8117279 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.0242. Min Act: -0.1700

Data Index: 2998478 (Open Web Text)

Max Activating Token Index: 686

Text #9

Max Range: 5.4077. Min Range: -5.4077

Max Act: 5.0227. Min Act: -0.1700

Data Index: 3493834 (Open Web Text)

Max Activating Token Index: 319

Text #10

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9855. Min Act: -0.1700

Data Index: 4461391 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9826. Min Act: -0.1700

Data Index: 6785901 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9923. Min Act: -0.1700

Data Index: 2848832 (Open Web Text)

Max Activating Token Index: 612

Text #13

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9195. Min Act: -0.1700

Data Index: 4460825 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9806. Min Act: -0.1700

Data Index: 7920297 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9352. Min Act: -0.1700

Data Index: 5673124 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.8900. Min Act: -0.1700

Data Index: 95192 (Open Web Text)

Max Activating Token Index: 669

Text #17

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9153. Min Act: -0.1700

Data Index: 793627 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.9104. Min Act: -0.1700

Data Index: 6050022 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 5.4077. Min Range: -5.4077

Max Act: 4.8935. Min Act: -0.1700

Data Index: 2295610 (Open Web Text)

Max Activating Token Index: 581