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

Dataset: Open Web Text

Neuron 1749 in Layer 1

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: 3.0080. Min Range: -3.0080

Max Act: 2.9885. Min Act: -0.1700

Data Index: 8001634 (Open Web Text)

Max Activating Token Index: 553

Text #1

Max Range: 3.0080. Min Range: -3.0080

Max Act: 3.0080. Min Act: -0.1700

Data Index: 4748061 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9922. Min Act: -0.1700

Data Index: 1223290 (Open Web Text)

Max Activating Token Index: 1017

Text #3

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9047. Min Act: -0.1700

Data Index: 1804600 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9021. Min Act: -0.1700

Data Index: 4825772 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8830. Min Act: -0.1700

Data Index: 793626 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9101. Min Act: -0.1700

Data Index: 8381986 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8731. Min Act: -0.1700

Data Index: 7788272 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8782. Min Act: -0.1700

Data Index: 1788628 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8789. Min Act: -0.1700

Data Index: 2092193 (Open Web Text)

Max Activating Token Index: 998

Text #10

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8545. Min Act: -0.1700

Data Index: 386677 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8814. Min Act: -0.1700

Data Index: 5990495 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8563. Min Act: -0.1700

Data Index: 861558 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8624. Min Act: -0.1700

Data Index: 2095706 (Open Web Text)

Max Activating Token Index: 213

Text #14

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8504. Min Act: -0.1700

Data Index: 8261107 (Open Web Text)

Max Activating Token Index: 725

Text #15

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8483. Min Act: -0.1700

Data Index: 8802923 (Open Web Text)

Max Activating Token Index: 184

Text #16

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8700. Min Act: -0.1700

Data Index: 176945 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8429. Min Act: -0.1700

Data Index: 2278774 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8201. Min Act: -0.1700

Data Index: 4847534 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8271. Min Act: -0.1700

Data Index: 61539 (Open Web Text)

Max Activating Token Index: 352