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

Dataset: Open Web Text

Neuron 1334 in Layer 4

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: 3.3561. Min Range: -3.3561

Max Act: 3.3561. Min Act: -0.1700

Data Index: 6642957 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3296. Min Act: -0.1700

Data Index: 7640680 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3102. Min Act: -0.1700

Data Index: 1325497 (Open Web Text)

Max Activating Token Index: 668

Text #3

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2452. Min Act: -0.1700

Data Index: 1039484 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2474. Min Act: -0.1700

Data Index: 724720 (Open Web Text)

Max Activating Token Index: 677

Text #5

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1905. Min Act: -0.1700

Data Index: 136127 (Open Web Text)

Max Activating Token Index: 596

Text #6

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1943. Min Act: -0.1700

Data Index: 1926863 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1830. Min Act: -0.1700

Data Index: 6626490 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1872. Min Act: -0.1700

Data Index: 2402787 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2002. Min Act: -0.1700

Data Index: 1077751 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1331131 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1762. Min Act: -0.1700

Data Index: 2277323 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1651. Min Act: -0.1700

Data Index: 5476511 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1621. Min Act: -0.1700

Data Index: 3893296 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1622. Min Act: -0.1700

Data Index: 6366881 (Open Web Text)

Max Activating Token Index: 780

Text #15

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1699. Min Act: -0.1700

Data Index: 7485176 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1481. Min Act: -0.1700

Data Index: 4033384 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1694. Min Act: -0.1700

Data Index: 5253871 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1891. Min Act: -0.1700

Data Index: 8700311 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1481. Min Act: -0.1700

Data Index: 443021 (Open Web Text)

Max Activating Token Index: 141