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

Dataset: Open Web Text

Neuron 348 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: 3.0941. Min Range: -3.0941

Max Act: 3.0941. Min Act: -0.1700

Data Index: 5114529 (Open Web Text)

Max Activating Token Index: 703

Text #1

Max Range: 3.0941. Min Range: -3.0941

Max Act: 3.0358. Min Act: -0.1700

Data Index: 2285872 (Open Web Text)

Max Activating Token Index: 627

Text #2

Max Range: 3.0941. Min Range: -3.0941

Max Act: 3.0603. Min Act: -0.1700

Data Index: 6659956 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9533. Min Act: -0.1700

Data Index: 5114539 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9766. Min Act: -0.1700

Data Index: 954159 (Open Web Text)

Max Activating Token Index: 859

Text #5

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9839. Min Act: -0.1700

Data Index: 2641558 (Open Web Text)

Max Activating Token Index: 244

Text #6

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9585. Min Act: -0.1700

Data Index: 5114544 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9634. Min Act: -0.1700

Data Index: 5467282 (Open Web Text)

Max Activating Token Index: 224

Text #8

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9631. Min Act: -0.1700

Data Index: 7105060 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9059. Min Act: -0.1700

Data Index: 4937228 (Open Web Text)

Max Activating Token Index: 495

Text #10

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9282. Min Act: -0.1700

Data Index: 6112822 (Open Web Text)

Max Activating Token Index: 471

Text #11

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9127. Min Act: -0.1700

Data Index: 3755519 (Open Web Text)

Max Activating Token Index: 923

Text #12

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9117. Min Act: -0.1700

Data Index: 5114558 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9325. Min Act: -0.1700

Data Index: 1041223 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.8936. Min Act: -0.1700

Data Index: 6351754 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9264. Min Act: -0.1700

Data Index: 7461110 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9121. Min Act: -0.1700

Data Index: 6537023 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9157. Min Act: -0.1700

Data Index: 3272891 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9072. Min Act: -0.1700

Data Index: 6752759 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 3.0941. Min Range: -3.0941

Max Act: 2.9372. Min Act: -0.1700

Data Index: 7914035 (Open Web Text)

Max Activating Token Index: 143