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

Dataset: Open Web Text

Neuron 1776 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: 3.0897. Min Range: -3.0897

Max Act: 3.0897. Min Act: -0.1700

Data Index: 6918016 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0558. Min Act: -0.1700

Data Index: 5257997 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0456. Min Act: -0.1700

Data Index: 20384 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0482. Min Act: -0.1700

Data Index: 1772826 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0262. Min Act: -0.1700

Data Index: 4605663 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0380. Min Act: -0.1700

Data Index: 4386766 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0147. Min Act: -0.1700

Data Index: 4336677 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0897. Min Range: -3.0897

Max Act: 3.0044. Min Act: -0.1700

Data Index: 5892684 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9907. Min Act: -0.1700

Data Index: 7317570 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9989. Min Act: -0.1700

Data Index: 3213959 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9768. Min Act: -0.1700

Data Index: 6383536 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9841. Min Act: -0.1700

Data Index: 165971 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9885. Min Act: -0.1700

Data Index: 6383547 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9782. Min Act: -0.1700

Data Index: 8314307 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9864. Min Act: -0.1700

Data Index: 6511044 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9828. Min Act: -0.1700

Data Index: 513654 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9673. Min Act: -0.1700

Data Index: 6947437 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9656. Min Act: -0.1700

Data Index: 5625775 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9656. Min Act: -0.1700

Data Index: 2986288 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.0897. Min Range: -3.0897

Max Act: 2.9689. Min Act: -0.1700

Data Index: 3370709 (Open Web Text)

Max Activating Token Index: 117