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

Dataset: Open Web Text

Neuron 534 in Layer 0

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: 5.8679. Min Range: -5.8679

Max Act: 5.8679. Min Act: -0.1700

Data Index: 1275217 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.8262. Min Act: -0.1700

Data Index: 5307091 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7303. Min Act: -0.1700

Data Index: 5255655 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7374. Min Act: -0.1700

Data Index: 5868327 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7276. Min Act: -0.1700

Data Index: 8693604 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6427. Min Act: -0.1700

Data Index: 6046481 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6565. Min Act: -0.1700

Data Index: 6046478 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6297. Min Act: -0.1700

Data Index: 7798227 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6428. Min Act: -0.1700

Data Index: 8485209 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6525. Min Act: -0.1700

Data Index: 1729490 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6088. Min Act: -0.1700

Data Index: 6351296 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5734. Min Act: -0.1700

Data Index: 6909459 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5521. Min Act: -0.1700

Data Index: 6046470 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5463. Min Act: -0.1700

Data Index: 7393905 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5456. Min Act: -0.1700

Data Index: 1047697 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5622. Min Act: -0.1700

Data Index: 4708604 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5397. Min Act: -0.1700

Data Index: 1826112 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5498. Min Act: -0.1700

Data Index: 1195445 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5103. Min Act: -0.1700

Data Index: 1347391 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.4855. Min Act: -0.1700

Data Index: 4100112 (Open Web Text)

Max Activating Token Index: 17