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

Dataset: Open Web Text

Neuron 2415 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: 3.0758. Min Range: -3.0758

Max Act: 3.0758. Min Act: -0.1700

Data Index: 4738997 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.9782. Min Act: -0.1700

Data Index: 6840108 (Open Web Text)

Max Activating Token Index: 720

Text #2

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8953. Min Act: -0.1700

Data Index: 7879593 (Open Web Text)

Max Activating Token Index: 580

Text #3

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8606. Min Act: -0.1700

Data Index: 8178795 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8333. Min Act: -0.1700

Data Index: 3623459 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8457. Min Act: -0.1700

Data Index: 1451563 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8190. Min Act: -0.1700

Data Index: 6428327 (Open Web Text)

Max Activating Token Index: 655

Text #7

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8267. Min Act: -0.1700

Data Index: 4640369 (Open Web Text)

Max Activating Token Index: 791

Text #8

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8146. Min Act: -0.1700

Data Index: 5442072 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8027. Min Act: -0.1700

Data Index: 5264624 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7918. Min Act: -0.1700

Data Index: 3150701 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8172. Min Act: -0.1700

Data Index: 2721232 (Open Web Text)

Max Activating Token Index: 691

Text #12

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7826. Min Act: -0.1700

Data Index: 6582502 (Open Web Text)

Max Activating Token Index: 679

Text #13

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.8148. Min Act: -0.1700

Data Index: 7753912 (Open Web Text)

Max Activating Token Index: 503

Text #14

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7892. Min Act: -0.1700

Data Index: 3883548 (Open Web Text)

Max Activating Token Index: 525

Text #15

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7499. Min Act: -0.1700

Data Index: 8481115 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7787. Min Act: -0.1700

Data Index: 8404047 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7728. Min Act: -0.1700

Data Index: 8713391 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7462. Min Act: -0.1700

Data Index: 4516418 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 3.0758. Min Range: -3.0758

Max Act: 2.7335. Min Act: -0.1700

Data Index: 3962302 (Open Web Text)

Max Activating Token Index: 813