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

Dataset: Open Web Text

Neuron 2513 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: 3.7393. Min Range: -3.7393

Max Act: 3.7393. Min Act: -0.1700

Data Index: 4922254 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7045. Min Act: -0.1700

Data Index: 6538823 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7109. Min Act: -0.1700

Data Index: 7459566 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7030. Min Act: -0.1700

Data Index: 8121244 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6884. Min Act: -0.1700

Data Index: 1701021 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6800. Min Act: -0.1700

Data Index: 8258575 (Open Web Text)

Max Activating Token Index: 341

Text #6

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6693. Min Act: -0.1700

Data Index: 8017198 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6558. Min Act: -0.1700

Data Index: 3468586 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6036. Min Act: -0.1700

Data Index: 1748961 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6006. Min Act: -0.1700

Data Index: 7882163 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6040. Min Act: -0.1700

Data Index: 6242916 (Open Web Text)

Max Activating Token Index: 565

Text #11

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5908. Min Act: -0.1700

Data Index: 3245971 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5939. Min Act: -0.1700

Data Index: 8623571 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5789. Min Act: -0.1700

Data Index: 4096064 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5780. Min Act: -0.1700

Data Index: 567548 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5575. Min Act: -0.1700

Data Index: 2996807 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5928. Min Act: -0.1700

Data Index: 5833703 (Open Web Text)

Max Activating Token Index: 626

Text #17

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5336. Min Act: -0.1700

Data Index: 1819391 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5717. Min Act: -0.1700

Data Index: 92220 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5369. Min Act: -0.1700

Data Index: 6851262 (Open Web Text)

Max Activating Token Index: 928