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

Dataset: Open Web Text

Neuron 2426 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: 1.2172. Min Range: -1.2172

Max Act: 1.2127. Min Act: -0.0537

Data Index: 7516988 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.2172. Min Act: -0.0671

Data Index: 574174 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.2004. Min Act: -0.0977

Data Index: 2891475 (Open Web Text)

Max Activating Token Index: 886

Text #3

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1951. Min Act: -0.0704

Data Index: 6777388 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1908. Min Act: -0.0830

Data Index: 1191365 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1923. Min Act: -0.1060

Data Index: 6008469 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1976. Min Act: -0.1017

Data Index: 4586110 (Open Web Text)

Max Activating Token Index: 902

Text #7

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1775. Min Act: -0.0674

Data Index: 947498 (Open Web Text)

Max Activating Token Index: 747

Text #8

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1687. Min Act: -0.0959

Data Index: 129286 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1743. Min Act: -0.0601

Data Index: 8446600 (Open Web Text)

Max Activating Token Index: 719

Text #10

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1749. Min Act: -0.0950

Data Index: 8179867 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1703. Min Act: -0.0823

Data Index: 2757655 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1750. Min Act: -0.0777

Data Index: 3212822 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1683. Min Act: -0.0641

Data Index: 7308589 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1731. Min Act: -0.0713

Data Index: 7140059 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1644. Min Act: -0.0346

Data Index: 711487 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1629. Min Act: -0.0330

Data Index: 5184693 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1660. Min Act: -0.0903

Data Index: 2460897 (Open Web Text)

Max Activating Token Index: 768

Text #18

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1618. Min Act: -0.1223

Data Index: 7020998 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1588. Min Act: -0.1464

Data Index: 2894449 (Open Web Text)

Max Activating Token Index: 7