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

Dataset: Open Web Text

Neuron 1717 in Layer 2

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: 1.0522. Min Range: -1.0522

Max Act: 1.0522. Min Act: -0.1700

Data Index: 7123741 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 1.0522. Min Range: -1.0522

Max Act: 1.0034. Min Act: -0.1685

Data Index: 4647416 (Open Web Text)

Max Activating Token Index: 807

Text #2

Max Range: 1.0522. Min Range: -1.0522

Max Act: 1.0031. Min Act: -0.1700

Data Index: 3424551 (Open Web Text)

Max Activating Token Index: 835

Text #3

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9933. Min Act: -0.1700

Data Index: 2758312 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9819. Min Act: -0.1700

Data Index: 7054951 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9767. Min Act: -0.1700

Data Index: 1421777 (Open Web Text)

Max Activating Token Index: 833

Text #6

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9856. Min Act: -0.1700

Data Index: 2714412 (Open Web Text)

Max Activating Token Index: 837

Text #7

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9860. Min Act: -0.1700

Data Index: 8374176 (Open Web Text)

Max Activating Token Index: 834

Text #8

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9852. Min Act: -0.1700

Data Index: 3521620 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9890. Min Act: -0.1700

Data Index: 7862233 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9865. Min Act: -0.1700

Data Index: 3063506 (Open Web Text)

Max Activating Token Index: 832

Text #11

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9756. Min Act: -0.1700

Data Index: 3755166 (Open Web Text)

Max Activating Token Index: 851

Text #12

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9785. Min Act: -0.1699

Data Index: 974100 (Open Web Text)

Max Activating Token Index: 832

Text #13

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9833. Min Act: -0.1700

Data Index: 1012048 (Open Web Text)

Max Activating Token Index: 817

Text #14

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9631. Min Act: -0.1700

Data Index: 3851265 (Open Web Text)

Max Activating Token Index: 825

Text #15

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9735. Min Act: -0.1700

Data Index: 2395158 (Open Web Text)

Max Activating Token Index: 804

Text #16

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9910. Min Act: -0.1700

Data Index: 2665212 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9767. Min Act: -0.1700

Data Index: 1331510 (Open Web Text)

Max Activating Token Index: 825

Text #18

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9795. Min Act: -0.1700

Data Index: 4163841 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9761. Min Act: -0.1700

Data Index: 2826321 (Open Web Text)

Max Activating Token Index: 841