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

Dataset: Open Web Text

Neuron 2593 in Layer 6

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: 3.3507. Min Range: -3.3507

Max Act: 3.3507. Min Act: -0.1700

Data Index: 2669217 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.3380. Min Act: -0.1700

Data Index: 5617970 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.3100. Min Act: -0.1700

Data Index: 7964001 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2595. Min Act: -0.1700

Data Index: 1769959 (Open Web Text)

Max Activating Token Index: 788

Text #4

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2607. Min Act: -0.1700

Data Index: 6631213 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2778. Min Act: -0.1700

Data Index: 5563360 (Open Web Text)

Max Activating Token Index: 432

Text #6

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2850. Min Act: -0.1700

Data Index: 1089391 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2165. Min Act: -0.1700

Data Index: 7630119 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2474. Min Act: -0.1700

Data Index: 2003956 (Open Web Text)

Max Activating Token Index: 505

Text #9

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2273. Min Act: -0.1700

Data Index: 8599495 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2225. Min Act: -0.1700

Data Index: 1552133 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2125. Min Act: -0.1700

Data Index: 3943866 (Open Web Text)

Max Activating Token Index: 110

Text #12

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2181. Min Act: -0.1700

Data Index: 4987051 (Open Web Text)

Max Activating Token Index: 943

Text #13

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2017. Min Act: -0.1700

Data Index: 1929946 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2054. Min Act: -0.1700

Data Index: 7402896 (Open Web Text)

Max Activating Token Index: 922

Text #15

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1770. Min Act: -0.1700

Data Index: 3034756 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1688. Min Act: -0.1700

Data Index: 7702809 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1845. Min Act: -0.1700

Data Index: 2603873 (Open Web Text)

Max Activating Token Index: 140

Text #18

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1665. Min Act: -0.1700

Data Index: 6874760 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1702. Min Act: -0.1700

Data Index: 7004607 (Open Web Text)

Max Activating Token Index: 7