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

Dataset: Open Web Text

Neuron 2981 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: 4.8676. Min Range: -4.8676

Max Act: 4.8557. Min Act: -0.1700

Data Index: 999794 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.8676. Min Act: -0.1700

Data Index: 1997461 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.8162. Min Act: -0.1700

Data Index: 7821598 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.7643. Min Act: -0.1700

Data Index: 1860459 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.7538. Min Act: -0.1700

Data Index: 2061073 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.7344. Min Act: -0.1700

Data Index: 6520890 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.7156. Min Act: -0.1700

Data Index: 6585669 (Open Web Text)

Max Activating Token Index: 397

Text #7

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.7073. Min Act: -0.1700

Data Index: 6873740 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.7129. Min Act: -0.1700

Data Index: 4244687 (Open Web Text)

Max Activating Token Index: 294

Text #9

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6588. Min Act: -0.1700

Data Index: 5342244 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6773. Min Act: -0.1700

Data Index: 2337946 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6941. Min Act: -0.1700

Data Index: 4306013 (Open Web Text)

Max Activating Token Index: 681

Text #12

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6663. Min Act: -0.1700

Data Index: 8020272 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6630. Min Act: -0.1700

Data Index: 603720 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6990. Min Act: -0.1700

Data Index: 7941903 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6704. Min Act: -0.1700

Data Index: 6137157 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6537. Min Act: -0.1700

Data Index: 2479635 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6334. Min Act: -0.1700

Data Index: 798345 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6504. Min Act: -0.1700

Data Index: 2768621 (Open Web Text)

Max Activating Token Index: 415

Text #19

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6551. Min Act: -0.1700

Data Index: 3931117 (Open Web Text)

Max Activating Token Index: 118