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

Dataset: Open Web Text

Neuron 2473 in Layer 5

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: 3.9079. Min Range: -3.9079

Max Act: 3.9079. Min Act: -0.1700

Data Index: 3285542 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.8882. Min Act: -0.1700

Data Index: 3674194 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.8642. Min Act: -0.1700

Data Index: 3055051 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.8508. Min Act: -0.1700

Data Index: 7009987 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7975. Min Act: -0.1700

Data Index: 7281303 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.8351. Min Act: -0.1700

Data Index: 482483 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7910. Min Act: -0.1700

Data Index: 2929791 (Open Web Text)

Max Activating Token Index: 217

Text #7

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7861. Min Act: -0.1700

Data Index: 2416945 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7313. Min Act: -0.1700

Data Index: 4564319 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7732. Min Act: -0.1700

Data Index: 466445 (Open Web Text)

Max Activating Token Index: 712

Text #10

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7545. Min Act: -0.1700

Data Index: 3856386 (Open Web Text)

Max Activating Token Index: 741

Text #11

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7395. Min Act: -0.1700

Data Index: 4745463 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7106. Min Act: -0.1700

Data Index: 6065645 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7308. Min Act: -0.1700

Data Index: 2203560 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7615. Min Act: -0.1700

Data Index: 1111199 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7059. Min Act: -0.1700

Data Index: 8660670 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6764. Min Act: -0.1700

Data Index: 4151601 (Open Web Text)

Max Activating Token Index: 442

Text #17

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7226. Min Act: -0.1700

Data Index: 3739551 (Open Web Text)

Max Activating Token Index: 661

Text #18

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6786. Min Act: -0.1700

Data Index: 801794 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6783. Min Act: -0.1700

Data Index: 3772278 (Open Web Text)

Max Activating Token Index: 301