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

Dataset: Open Web Text

Neuron 1115 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: 2.1168. Min Range: -2.1168

Max Act: 2.1168. Min Act: -0.1700

Data Index: 2618597 (Open Web Text)

Max Activating Token Index: 649

Text #1

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0925. Min Act: -0.1700

Data Index: 1848 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0786. Min Act: -0.1700

Data Index: 2415020 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0689. Min Act: -0.1700

Data Index: 5912653 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0686. Min Act: -0.1700

Data Index: 1815585 (Open Web Text)

Max Activating Token Index: 654

Text #5

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0599. Min Act: -0.1700

Data Index: 3150500 (Open Web Text)

Max Activating Token Index: 657

Text #6

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0221. Min Act: -0.1700

Data Index: 1494879 (Open Web Text)

Max Activating Token Index: 669

Text #7

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0313. Min Act: -0.1700

Data Index: 5643782 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0171. Min Act: -0.1700

Data Index: 3587466 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9996. Min Act: -0.1700

Data Index: 6600718 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0109. Min Act: -0.1700

Data Index: 8560841 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0054. Min Act: -0.1700

Data Index: 3402676 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 2.1168. Min Range: -2.1168

Max Act: 2.0051. Min Act: -0.1700

Data Index: 6674364 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9946. Min Act: -0.1700

Data Index: 4166313 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9820. Min Act: -0.1700

Data Index: 5053903 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9555. Min Act: -0.1700

Data Index: 2861501 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9886. Min Act: -0.1700

Data Index: 1720400 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9648. Min Act: -0.1700

Data Index: 7105536 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9723. Min Act: -0.1700

Data Index: 4470377 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 2.1168. Min Range: -2.1168

Max Act: 1.9645. Min Act: -0.1700

Data Index: 689714 (Open Web Text)

Max Activating Token Index: 647