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

Dataset: Open Web Text

Neuron 2603 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: 1.7559. Min Range: -1.7559

Max Act: 1.7559. Min Act: -0.1700

Data Index: 3136206 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6928. Min Act: -0.1700

Data Index: 8521785 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.7010. Min Act: -0.1700

Data Index: 415328 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6946. Min Act: -0.1700

Data Index: 5515947 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6874. Min Act: -0.1700

Data Index: 5108560 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6762. Min Act: -0.1700

Data Index: 7521340 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6645. Min Act: -0.1700

Data Index: 8521786 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6657. Min Act: -0.1700

Data Index: 6948667 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6700. Min Act: -0.1700

Data Index: 8417708 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6614. Min Act: -0.1700

Data Index: 3922106 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6579. Min Act: -0.1700

Data Index: 2595956 (Open Web Text)

Max Activating Token Index: 568

Text #11

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6582. Min Act: -0.1700

Data Index: 13241 (Open Web Text)

Max Activating Token Index: 319

Text #12

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6516. Min Act: -0.1700

Data Index: 2813308 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6482. Min Act: -0.1700

Data Index: 1436720 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6447. Min Act: -0.1698

Data Index: 3791062 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6461. Min Act: -0.1700

Data Index: 4752244 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6407. Min Act: -0.1700

Data Index: 8281683 (Open Web Text)

Max Activating Token Index: 963

Text #17

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6454. Min Act: -0.1700

Data Index: 3032153 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6408. Min Act: -0.1700

Data Index: 1074742 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6475. Min Act: -0.1700

Data Index: 1140055 (Open Web Text)

Max Activating Token Index: 709