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

Dataset: Open Web Text

Neuron 128 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: 3.4499. Min Range: -3.4499

Max Act: 3.4499. Min Act: -0.1700

Data Index: 660319 (Open Web Text)

Max Activating Token Index: 941

Text #1

Max Range: 3.4499. Min Range: -3.4499

Max Act: 3.0912. Min Act: -0.1700

Data Index: 5330830 (Open Web Text)

Max Activating Token Index: 738

Text #2

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.9732. Min Act: -0.1700

Data Index: 8283925 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.9297. Min Act: -0.1700

Data Index: 5329600 (Open Web Text)

Max Activating Token Index: 405

Text #4

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8875. Min Act: -0.1700

Data Index: 1117070 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8740. Min Act: -0.1700

Data Index: 7993449 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8722. Min Act: -0.1700

Data Index: 7280427 (Open Web Text)

Max Activating Token Index: 170

Text #7

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8697. Min Act: -0.1700

Data Index: 7864801 (Open Web Text)

Max Activating Token Index: 416

Text #8

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8032. Min Act: -0.1700

Data Index: 487966 (Open Web Text)

Max Activating Token Index: 961

Text #9

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8479. Min Act: -0.1700

Data Index: 5333492 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.7384. Min Act: -0.1700

Data Index: 3389972 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8325. Min Act: -0.1700

Data Index: 1378768 (Open Web Text)

Max Activating Token Index: 776

Text #12

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8459. Min Act: -0.1700

Data Index: 3571510 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8247. Min Act: -0.1700

Data Index: 1564311 (Open Web Text)

Max Activating Token Index: 272

Text #14

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.7990. Min Act: -0.1700

Data Index: 296520 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.6609. Min Act: -0.1700

Data Index: 6717653 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8330. Min Act: -0.1700

Data Index: 7409585 (Open Web Text)

Max Activating Token Index: 351

Text #17

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8514. Min Act: -0.1700

Data Index: 6258821 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.8448. Min Act: -0.1700

Data Index: 1981991 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 3.4499. Min Range: -3.4499

Max Act: 2.7627. Min Act: -0.1700

Data Index: 3523576 (Open Web Text)

Max Activating Token Index: 413