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

Dataset: Open Web Text

Neuron 1937 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: 1.7030. Min Range: -1.7030

Max Act: 1.7030. Min Act: -0.1700

Data Index: 4526832 (Open Web Text)

Max Activating Token Index: 415

Text #1

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.6039. Min Act: -0.1697

Data Index: 2227213 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.6003. Min Act: -0.1700

Data Index: 7204971 (Open Web Text)

Max Activating Token Index: 890

Text #3

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5920. Min Act: -0.1700

Data Index: 7393015 (Open Web Text)

Max Activating Token Index: 253

Text #4

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.6033. Min Act: -0.1700

Data Index: 6556704 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5837. Min Act: -0.1700

Data Index: 6998872 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5936. Min Act: -0.1700

Data Index: 2441620 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5833. Min Act: -0.1700

Data Index: 6052879 (Open Web Text)

Max Activating Token Index: 82

Text #8

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5852. Min Act: -0.1700

Data Index: 5651640 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5721. Min Act: -0.1700

Data Index: 173525 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5727. Min Act: -0.1700

Data Index: 8162782 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5690. Min Act: -0.1700

Data Index: 5638868 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5727. Min Act: -0.1700

Data Index: 2963500 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5722. Min Act: -0.1691

Data Index: 5951960 (Open Web Text)

Max Activating Token Index: 980

Text #14

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5699. Min Act: -0.1700

Data Index: 6929 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5729. Min Act: -0.1700

Data Index: 8570309 (Open Web Text)

Max Activating Token Index: 373

Text #16

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5785. Min Act: -0.1700

Data Index: 2558857 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5814. Min Act: -0.1700

Data Index: 4175286 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5733. Min Act: -0.1700

Data Index: 7221178 (Open Web Text)

Max Activating Token Index: 940

Text #19

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.5640. Min Act: -0.1700

Data Index: 880475 (Open Web Text)

Max Activating Token Index: 133