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

Dataset: Open Web Text

Neuron 454 in Layer 5

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: 3.3849. Min Range: -3.3849

Max Act: 3.3849. Min Act: -0.1700

Data Index: 6559956 (Open Web Text)

Max Activating Token Index: 972

Text #1

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.3456. Min Act: -0.1700

Data Index: 1904382 (Open Web Text)

Max Activating Token Index: 62

Text #2

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2901. Min Act: -0.1700

Data Index: 7629578 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2725. Min Act: -0.1700

Data Index: 6408495 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2608. Min Act: -0.1700

Data Index: 7414612 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2553. Min Act: -0.1700

Data Index: 8116798 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2644. Min Act: -0.1700

Data Index: 8618746 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2420. Min Act: -0.1700

Data Index: 4657779 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2139. Min Act: -0.1700

Data Index: 2684087 (Open Web Text)

Max Activating Token Index: 740

Text #9

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2690. Min Act: -0.1700

Data Index: 2131825 (Open Web Text)

Max Activating Token Index: 572

Text #10

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.1975. Min Act: -0.1700

Data Index: 1229890 (Open Web Text)

Max Activating Token Index: 352

Text #11

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2056. Min Act: -0.1700

Data Index: 4976416 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2345. Min Act: -0.1700

Data Index: 524728 (Open Web Text)

Max Activating Token Index: 228

Text #13

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2069. Min Act: -0.1700

Data Index: 2853309 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2024. Min Act: -0.1700

Data Index: 801908 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2127. Min Act: -0.1700

Data Index: 3595087 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2341. Min Act: -0.1700

Data Index: 497003 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2098. Min Act: -0.1700

Data Index: 4491107 (Open Web Text)

Max Activating Token Index: 101

Text #18

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2011. Min Act: -0.1700

Data Index: 1223356 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2175. Min Act: -0.1700

Data Index: 1079785 (Open Web Text)

Max Activating Token Index: 329