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

Dataset: Open Web Text

Neuron 823 in Layer 4

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: 2.9949. Min Range: -2.9949

Max Act: 2.9801. Min Act: -0.1700

Data Index: 7265247 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9949. Min Act: -0.1700

Data Index: 849116 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9647. Min Act: -0.1700

Data Index: 2470520 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9472. Min Act: -0.1700

Data Index: 6578257 (Open Web Text)

Max Activating Token Index: 755

Text #4

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9564. Min Act: -0.1700

Data Index: 925174 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9257. Min Act: -0.1700

Data Index: 2894714 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9088. Min Act: -0.1700

Data Index: 2983981 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9291. Min Act: -0.1700

Data Index: 6981037 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9054. Min Act: -0.1700

Data Index: 7343309 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9295. Min Act: -0.1700

Data Index: 5662379 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8932. Min Act: -0.1700

Data Index: 2850756 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9162. Min Act: -0.1700

Data Index: 7519511 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8881. Min Act: -0.1700

Data Index: 5522611 (Open Web Text)

Max Activating Token Index: 981

Text #13

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8998. Min Act: -0.1700

Data Index: 8162695 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9088. Min Act: -0.1700

Data Index: 455794 (Open Web Text)

Max Activating Token Index: 588

Text #15

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8960. Min Act: -0.1700

Data Index: 8284788 (Open Web Text)

Max Activating Token Index: 661

Text #16

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8731. Min Act: -0.1700

Data Index: 4226582 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.9059. Min Act: -0.1700

Data Index: 2620478 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8633. Min Act: -0.1700

Data Index: 3718979 (Open Web Text)

Max Activating Token Index: 486

Text #19

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.8752. Min Act: -0.1700

Data Index: 171788 (Open Web Text)

Max Activating Token Index: 808