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

Dataset: Open Web Text

Neuron 748 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: 3.3650. Min Range: -3.3650

Max Act: 3.3650. Min Act: -0.1700

Data Index: 1869866 (Open Web Text)

Max Activating Token Index: 260

Text #1

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.3375. Min Act: -0.1700

Data Index: 6551298 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.3083. Min Act: -0.1700

Data Index: 5531159 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2979. Min Act: -0.1700

Data Index: 6740729 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2942. Min Act: -0.1700

Data Index: 6553014 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.3035. Min Act: -0.1700

Data Index: 1946466 (Open Web Text)

Max Activating Token Index: 94

Text #6

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2928. Min Act: -0.1700

Data Index: 8687990 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2750. Min Act: -0.1700

Data Index: 5392639 (Open Web Text)

Max Activating Token Index: 930

Text #8

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2762. Min Act: -0.1700

Data Index: 4597988 (Open Web Text)

Max Activating Token Index: 250

Text #9

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2439. Min Act: -0.1700

Data Index: 3651496 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2646. Min Act: -0.1700

Data Index: 3311209 (Open Web Text)

Max Activating Token Index: 404

Text #11

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2794. Min Act: -0.1700

Data Index: 598087 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2711. Min Act: -0.1700

Data Index: 1740265 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2395. Min Act: -0.1700

Data Index: 3311734 (Open Web Text)

Max Activating Token Index: 566

Text #14

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2600. Min Act: -0.1700

Data Index: 4029496 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2637. Min Act: -0.1700

Data Index: 831163 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2501. Min Act: -0.1700

Data Index: 6373856 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2492. Min Act: -0.1700

Data Index: 3030306 (Open Web Text)

Max Activating Token Index: 331

Text #18

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2579. Min Act: -0.1700

Data Index: 282756 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2593. Min Act: -0.1700

Data Index: 2909219 (Open Web Text)

Max Activating Token Index: 392