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

Dataset: Open Web Text

Neuron 560 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: 5.8034. Min Range: -5.8034

Max Act: 5.8034. Min Act: -0.1700

Data Index: 220831 (Open Web Text)

Max Activating Token Index: 792

Text #1

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6368. Min Act: -0.1700

Data Index: 6731889 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6937. Min Act: -0.1700

Data Index: 2196838 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6764. Min Act: -0.1700

Data Index: 6620215 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6611. Min Act: -0.1700

Data Index: 3555463 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6112. Min Act: -0.1700

Data Index: 2231783 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6262. Min Act: -0.1700

Data Index: 185696 (Open Web Text)

Max Activating Token Index: 944

Text #7

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6023. Min Act: -0.1700

Data Index: 3929633 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.6084. Min Act: -0.1700

Data Index: 1441668 (Open Web Text)

Max Activating Token Index: 986

Text #9

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.5239. Min Act: -0.1700

Data Index: 444095 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4614. Min Act: -0.1700

Data Index: 8577084 (Open Web Text)

Max Activating Token Index: 555

Text #11

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4831. Min Act: -0.1700

Data Index: 4840454 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4308. Min Act: -0.1700

Data Index: 6695659 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4542. Min Act: -0.1700

Data Index: 258985 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4643. Min Act: -0.1700

Data Index: 1836833 (Open Web Text)

Max Activating Token Index: 228

Text #15

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4102. Min Act: -0.1700

Data Index: 3149592 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.4481. Min Act: -0.1700

Data Index: 5727444 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.3947. Min Act: -0.1700

Data Index: 8321666 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.3768. Min Act: -0.1700

Data Index: 8579685 (Open Web Text)

Max Activating Token Index: 98

Text #19

Max Range: 5.8034. Min Range: -5.8034

Max Act: 5.3769. Min Act: -0.1700

Data Index: 5375885 (Open Web Text)

Max Activating Token Index: 433