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

Dataset: Open Web Text

Neuron 415 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: 3.2620. Min Range: -3.2620

Max Act: 3.2620. Min Act: -0.1700

Data Index: 5063567 (Open Web Text)

Max Activating Token Index: 892

Text #1

Max Range: 3.2620. Min Range: -3.2620

Max Act: 3.0587. Min Act: -0.1700

Data Index: 3167751 (Open Web Text)

Max Activating Token Index: 843

Text #2

Max Range: 3.2620. Min Range: -3.2620

Max Act: 3.0621. Min Act: -0.1700

Data Index: 3974579 (Open Web Text)

Max Activating Token Index: 732

Text #3

Max Range: 3.2620. Min Range: -3.2620

Max Act: 3.0707. Min Act: -0.1700

Data Index: 3167748 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 3.2620. Min Range: -3.2620

Max Act: 3.0080. Min Act: -0.1700

Data Index: 2810189 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9765. Min Act: -0.1700

Data Index: 4445910 (Open Web Text)

Max Activating Token Index: 235

Text #6

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9436. Min Act: -0.1700

Data Index: 707565 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9325. Min Act: -0.1700

Data Index: 7358774 (Open Web Text)

Max Activating Token Index: 922

Text #8

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9132. Min Act: -0.1700

Data Index: 3932484 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9246. Min Act: -0.1700

Data Index: 555820 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9030. Min Act: -0.1700

Data Index: 2194777 (Open Web Text)

Max Activating Token Index: 212

Text #11

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.9212. Min Act: -0.1700

Data Index: 3561865 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8938. Min Act: -0.1700

Data Index: 6668520 (Open Web Text)

Max Activating Token Index: 296

Text #13

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8611. Min Act: -0.1700

Data Index: 5513586 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8378. Min Act: -0.1700

Data Index: 56733 (Open Web Text)

Max Activating Token Index: 264

Text #15

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8311. Min Act: -0.1700

Data Index: 3355022 (Open Web Text)

Max Activating Token Index: 674

Text #16

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8476. Min Act: -0.1700

Data Index: 3831515 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8354. Min Act: -0.1700

Data Index: 2048655 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8308. Min Act: -0.1700

Data Index: 1793496 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 3.2620. Min Range: -3.2620

Max Act: 2.8497. Min Act: -0.1700

Data Index: 181030 (Open Web Text)

Max Activating Token Index: 476