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

Dataset: Open Web Text

Neuron 2023 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: 4.0283. Min Range: -4.0283

Max Act: 4.0283. Min Act: -0.1700

Data Index: 7171606 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.9828. Min Act: -0.1700

Data Index: 1737009 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.9242. Min Act: -0.1700

Data Index: 6849476 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.8756. Min Act: -0.1700

Data Index: 6122210 (Open Web Text)

Max Activating Token Index: 138

Text #4

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.9017. Min Act: -0.1700

Data Index: 8142197 (Open Web Text)

Max Activating Token Index: 781

Text #5

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.8138. Min Act: -0.1700

Data Index: 2857422 (Open Web Text)

Max Activating Token Index: 203

Text #6

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7996. Min Act: -0.1700

Data Index: 4605054 (Open Web Text)

Max Activating Token Index: 655

Text #7

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7805. Min Act: -0.1700

Data Index: 3894075 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.8215. Min Act: -0.1700

Data Index: 8373814 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7962. Min Act: -0.1700

Data Index: 7499492 (Open Web Text)

Max Activating Token Index: 673

Text #10

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.8084. Min Act: -0.1700

Data Index: 1222144 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7978. Min Act: -0.1700

Data Index: 149637 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.8079. Min Act: -0.1700

Data Index: 6654109 (Open Web Text)

Max Activating Token Index: 218

Text #13

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7481. Min Act: -0.1700

Data Index: 6163524 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.8104. Min Act: -0.1700

Data Index: 6039000 (Open Web Text)

Max Activating Token Index: 502

Text #15

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7623. Min Act: -0.1700

Data Index: 506810 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7572. Min Act: -0.1700

Data Index: 1292389 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7831. Min Act: -0.1700

Data Index: 3016006 (Open Web Text)

Max Activating Token Index: 852

Text #18

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7571. Min Act: -0.1700

Data Index: 6521459 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 4.0283. Min Range: -4.0283

Max Act: 3.7493. Min Act: -0.1700

Data Index: 3975598 (Open Web Text)

Max Activating Token Index: 293