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

Dataset: Open Web Text

Neuron 1744 in Layer 0

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: 2.9433. Min Range: -2.9433

Max Act: 2.9317. Min Act: -0.1700

Data Index: 1988999 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9433. Min Act: -0.1700

Data Index: 3569988 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1414536 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9129. Min Act: -0.1700

Data Index: 1551812 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9007. Min Act: -0.1700

Data Index: 1607063 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9095. Min Act: -0.1700

Data Index: 5272483 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9095. Min Act: -0.1700

Data Index: 3354400 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9078. Min Act: -0.1700

Data Index: 676316 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9084. Min Act: -0.1700

Data Index: 3391037 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8943. Min Act: -0.1700

Data Index: 386520 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8986. Min Act: -0.1700

Data Index: 3814233 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8771. Min Act: -0.1700

Data Index: 2835591 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8928. Min Act: -0.1700

Data Index: 2757958 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8819. Min Act: -0.1700

Data Index: 2424475 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8813. Min Act: -0.1700

Data Index: 8001374 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8701. Min Act: -0.1700

Data Index: 3852269 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8786. Min Act: -0.1700

Data Index: 4273768 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8701. Min Act: -0.1700

Data Index: 3768208 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8809. Min Act: -0.1700

Data Index: 412692 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.8750. Min Act: -0.1700

Data Index: 1272833 (Open Web Text)

Max Activating Token Index: 5