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

Dataset: Open Web Text

Neuron 67 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: 1.7246. Min Range: -1.7246

Max Act: 1.7246. Min Act: -0.1018

Data Index: 1028875 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.7240. Min Act: -0.1688

Data Index: 8014238 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.7230. Min Act: -0.1670

Data Index: 3169830 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.7222. Min Act: -0.1610

Data Index: 2399971 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.7096. Min Act: -0.1630

Data Index: 6362438 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6947. Min Act: -0.1670

Data Index: 8209382 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.7036. Min Act: -0.1678

Data Index: 1151003 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6832. Min Act: -0.1532

Data Index: 6524531 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6911. Min Act: -0.1626

Data Index: 4751082 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6851. Min Act: -0.1635

Data Index: 1840848 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6777. Min Act: -0.1696

Data Index: 7020811 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6783. Min Act: -0.1624

Data Index: 4938402 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6729. Min Act: -0.1655

Data Index: 7553446 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6761. Min Act: -0.1694

Data Index: 4811113 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6681. Min Act: -0.1351

Data Index: 1034906 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6587. Min Act: -0.1692

Data Index: 1296239 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6643. Min Act: -0.1681

Data Index: 917674 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6564. Min Act: -0.1610

Data Index: 1352166 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6599. Min Act: -0.1614

Data Index: 5040458 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 1.7246. Min Range: -1.7246

Max Act: 1.6569. Min Act: -0.1621

Data Index: 476018 (Open Web Text)

Max Activating Token Index: 524