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

Dataset: Open Web Text

Neuron 1824 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: 1.0613. Min Range: -1.0613

Max Act: 1.0613. Min Act: -0.1700

Data Index: 8725030 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9321. Min Act: -0.1700

Data Index: 2793882 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9321. Min Act: -0.1700

Data Index: 7855401 (Open Web Text)

Max Activating Token Index: 892

Text #3

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9285. Min Act: -0.1700

Data Index: 6735326 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9167. Min Act: -0.1700

Data Index: 8403886 (Open Web Text)

Max Activating Token Index: 935

Text #5

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8806. Min Act: -0.1700

Data Index: 8179580 (Open Web Text)

Max Activating Token Index: 918

Text #6

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8887. Min Act: -0.1700

Data Index: 2793726 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8921. Min Act: -0.1700

Data Index: 1510447 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8882. Min Act: -0.1700

Data Index: 3669912 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8867. Min Act: -0.1700

Data Index: 6790602 (Open Web Text)

Max Activating Token Index: 894

Text #10

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8884. Min Act: -0.1700

Data Index: 2299745 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8756. Min Act: -0.1700

Data Index: 5448044 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8800. Min Act: -0.1700

Data Index: 8336814 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8689. Min Act: -0.1700

Data Index: 4122776 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8638. Min Act: -0.1700

Data Index: 959602 (Open Web Text)

Max Activating Token Index: 287

Text #15

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8538. Min Act: -0.1700

Data Index: 3245788 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8629. Min Act: -0.1700

Data Index: 2227861 (Open Web Text)

Max Activating Token Index: 941

Text #17

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8647. Min Act: -0.1700

Data Index: 136276 (Open Web Text)

Max Activating Token Index: 887

Text #18

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8751. Min Act: -0.1700

Data Index: 2624243 (Open Web Text)

Max Activating Token Index: 901

Text #19

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8379. Min Act: -0.1700

Data Index: 4437586 (Open Web Text)

Max Activating Token Index: 894