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

Dataset: Open Web Text

Neuron 2938 in Layer 6

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: 4.7477. Min Range: -4.7477

Max Act: 4.7477. Min Act: -0.1700

Data Index: 6211057 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.6930. Min Act: -0.1700

Data Index: 4983672 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.4333. Min Act: -0.1700

Data Index: 4779067 (Open Web Text)

Max Activating Token Index: 172

Text #3

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.4139. Min Act: -0.1700

Data Index: 6255760 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.3361. Min Act: -0.1700

Data Index: 3739456 (Open Web Text)

Max Activating Token Index: 673

Text #5

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.3850. Min Act: -0.1700

Data Index: 4731973 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.2430. Min Act: -0.1700

Data Index: 1799202 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.2811. Min Act: -0.1700

Data Index: 7800816 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.2431. Min Act: -0.1700

Data Index: 8149516 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.1321. Min Act: -0.1700

Data Index: 4105084 (Open Web Text)

Max Activating Token Index: 131

Text #10

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.1149. Min Act: -0.1700

Data Index: 1362100 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.1036. Min Act: -0.1700

Data Index: 3230817 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.2167. Min Act: -0.1700

Data Index: 108361 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.0591. Min Act: -0.1700

Data Index: 4087337 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.1293. Min Act: -0.1700

Data Index: 8057328 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.0307. Min Act: -0.1700

Data Index: 7563984 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.0177. Min Act: -0.1700

Data Index: 1595463 (Open Web Text)

Max Activating Token Index: 885

Text #17

Max Range: 4.7477. Min Range: -4.7477

Max Act: 3.9463. Min Act: -0.1700

Data Index: 5498139 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 4.7477. Min Range: -4.7477

Max Act: 4.0479. Min Act: -0.1700

Data Index: 5843290 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 4.7477. Min Range: -4.7477

Max Act: 3.8745. Min Act: -0.1700

Data Index: 6299651 (Open Web Text)

Max Activating Token Index: 580