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

Dataset: Open Web Text

Neuron 2293 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: 4.1499. Min Range: -4.1499

Max Act: 4.1280. Min Act: -0.1700

Data Index: 7228093 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.1179. Min Act: -0.1700

Data Index: 1933582 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.1499. Min Act: -0.1700

Data Index: 3629125 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0587. Min Act: -0.1700

Data Index: 8829417 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0918. Min Act: -0.1700

Data Index: 4418398 (Open Web Text)

Max Activating Token Index: 140

Text #5

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0862. Min Act: -0.1700

Data Index: 2954336 (Open Web Text)

Max Activating Token Index: 730

Text #6

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0521. Min Act: -0.1700

Data Index: 1285621 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0261. Min Act: -0.1700

Data Index: 7113930 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0127. Min Act: -0.1700

Data Index: 4442410 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0318. Min Act: -0.1700

Data Index: 6053770 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 4.1499. Min Range: -4.1499

Max Act: 4.0012. Min Act: -0.1700

Data Index: 6129807 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9837. Min Act: -0.1700

Data Index: 5130079 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9933. Min Act: -0.1700

Data Index: 5212709 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9644. Min Act: -0.1700

Data Index: 8791788 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9787. Min Act: -0.1700

Data Index: 3891771 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9391. Min Act: -0.1700

Data Index: 8633556 (Open Web Text)

Max Activating Token Index: 858

Text #16

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9346. Min Act: -0.1700

Data Index: 7770101 (Open Web Text)

Max Activating Token Index: 911

Text #17

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9508. Min Act: -0.1700

Data Index: 2828001 (Open Web Text)

Max Activating Token Index: 825

Text #18

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9633. Min Act: -0.1700

Data Index: 7733728 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 4.1499. Min Range: -4.1499

Max Act: 3.9501. Min Act: -0.1700

Data Index: 7231401 (Open Web Text)

Max Activating Token Index: 568