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

Dataset: Open Web Text

Neuron 2771 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: 4.3682. Min Range: -4.3682

Max Act: 4.3682. Min Act: -0.1700

Data Index: 5773817 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.3216. Min Act: -0.1700

Data Index: 6226230 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.2812. Min Act: -0.1700

Data Index: 920243 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.2859. Min Act: -0.1700

Data Index: 1597237 (Open Web Text)

Max Activating Token Index: 115

Text #4

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.2377. Min Act: -0.1700

Data Index: 5140805 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.2454. Min Act: -0.1700

Data Index: 3144037 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1994. Min Act: -0.1700

Data Index: 3273975 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.2145. Min Act: -0.1700

Data Index: 1979262 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.2015. Min Act: -0.1700

Data Index: 5223932 (Open Web Text)

Max Activating Token Index: 678

Text #9

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1741. Min Act: -0.1700

Data Index: 881531 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1465. Min Act: -0.1700

Data Index: 3193242 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1443. Min Act: -0.1700

Data Index: 8557219 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1533. Min Act: -0.1700

Data Index: 2408076 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1551. Min Act: -0.1700

Data Index: 5286424 (Open Web Text)

Max Activating Token Index: 870

Text #14

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1087. Min Act: -0.1700

Data Index: 5710005 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1409. Min Act: -0.1700

Data Index: 3980127 (Open Web Text)

Max Activating Token Index: 1004

Text #16

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1313. Min Act: -0.1700

Data Index: 197521 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1549. Min Act: -0.1700

Data Index: 1513610 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1148. Min Act: -0.1700

Data Index: 2043904 (Open Web Text)

Max Activating Token Index: 554

Text #19

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.0986. Min Act: -0.1700

Data Index: 2983642 (Open Web Text)

Max Activating Token Index: 953