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

Dataset: Open Web Text

Neuron 1392 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: 4.1633. Min Range: -4.1633

Max Act: 4.1633. Min Act: -0.1700

Data Index: 625066 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.1633. Min Range: -4.1633

Max Act: 4.0266. Min Act: -0.1700

Data Index: 6054135 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9822. Min Act: -0.1700

Data Index: 2662665 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9768. Min Act: -0.1700

Data Index: 1721697 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9823. Min Act: -0.1700

Data Index: 281246 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9963. Min Act: -0.1700

Data Index: 8069287 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9896. Min Act: -0.1700

Data Index: 7422477 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9712. Min Act: -0.1700

Data Index: 2666378 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9470. Min Act: -0.1700

Data Index: 5987815 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9546. Min Act: -0.1700

Data Index: 5831444 (Open Web Text)

Max Activating Token Index: 62

Text #10

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9506. Min Act: -0.1700

Data Index: 5771922 (Open Web Text)

Max Activating Token Index: 178

Text #11

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9662. Min Act: -0.1700

Data Index: 6397883 (Open Web Text)

Max Activating Token Index: 78

Text #12

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9653. Min Act: -0.1700

Data Index: 1867649 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9374. Min Act: -0.1700

Data Index: 2323411 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9247. Min Act: -0.1700

Data Index: 6811877 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9034. Min Act: -0.1700

Data Index: 6664626 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9538. Min Act: -0.1700

Data Index: 6424617 (Open Web Text)

Max Activating Token Index: 528

Text #17

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9166. Min Act: -0.1700

Data Index: 4602580 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9525. Min Act: -0.1700

Data Index: 408034 (Open Web Text)

Max Activating Token Index: 118

Text #19

Max Range: 4.1633. Min Range: -4.1633

Max Act: 3.9035. Min Act: -0.1700

Data Index: 6180769 (Open Web Text)

Max Activating Token Index: 552