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

Dataset: Open Web Text

Neuron 1310 in Layer 3

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: 1.7726. Min Range: -1.7726

Max Act: 1.7726. Min Act: -0.1694

Data Index: 545589 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7351. Min Act: -0.1700

Data Index: 846007 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7393. Min Act: -0.1698

Data Index: 1321395 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6997. Min Act: -0.1697

Data Index: 1550712 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7110. Min Act: -0.1700

Data Index: 896318 (Open Web Text)

Max Activating Token Index: 259

Text #5

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7022. Min Act: -0.1692

Data Index: 6783676 (Open Web Text)

Max Activating Token Index: 859

Text #6

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7011. Min Act: -0.1695

Data Index: 2063861 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6927. Min Act: -0.1700

Data Index: 7914266 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6829. Min Act: -0.1699

Data Index: 1741164 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6800. Min Act: -0.1700

Data Index: 6379941 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6737. Min Act: -0.1687

Data Index: 7324968 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6782. Min Act: -0.1700

Data Index: 597856 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6578. Min Act: -0.1697

Data Index: 7413134 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6685. Min Act: -0.1697

Data Index: 1856668 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6643. Min Act: -0.1700

Data Index: 4122622 (Open Web Text)

Max Activating Token Index: 896

Text #15

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6694. Min Act: -0.1700

Data Index: 8157361 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6655. Min Act: -0.1700

Data Index: 3607320 (Open Web Text)

Max Activating Token Index: 303

Text #17

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6647. Min Act: -0.1700

Data Index: 6662494 (Open Web Text)

Max Activating Token Index: 751

Text #18

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6536. Min Act: -0.1698

Data Index: 5896988 (Open Web Text)

Max Activating Token Index: 808

Text #19

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.6654. Min Act: -0.1700

Data Index: 1804218 (Open Web Text)

Max Activating Token Index: 133