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

Dataset: Open Web Text

Neuron 372 in Layer 2

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: 3.9215. Min Range: -3.9215

Max Act: 3.9215. Min Act: -0.1700

Data Index: 870701 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.8474. Min Act: -0.1700

Data Index: 8675866 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.7166. Min Act: -0.1700

Data Index: 2878797 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.7585. Min Act: -0.1700

Data Index: 478031 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.7500. Min Act: -0.1700

Data Index: 7874765 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6957. Min Act: -0.1700

Data Index: 5429612 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.7097. Min Act: -0.1700

Data Index: 1021952 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.7401. Min Act: -0.1700

Data Index: 6849930 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6825. Min Act: -0.1700

Data Index: 7289308 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6777. Min Act: -0.1700

Data Index: 1194617 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6882. Min Act: -0.1700

Data Index: 2243829 (Open Web Text)

Max Activating Token Index: 235

Text #11

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6718. Min Act: -0.1700

Data Index: 6576201 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6764. Min Act: -0.1700

Data Index: 1584385 (Open Web Text)

Max Activating Token Index: 911

Text #13

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6686. Min Act: -0.1700

Data Index: 6204651 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6546. Min Act: -0.1700

Data Index: 5433570 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6363. Min Act: -0.1700

Data Index: 3990094 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6430. Min Act: -0.1700

Data Index: 4216332 (Open Web Text)

Max Activating Token Index: 276

Text #17

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6552. Min Act: -0.1700

Data Index: 3320971 (Open Web Text)

Max Activating Token Index: 810

Text #18

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6462. Min Act: -0.1700

Data Index: 6804984 (Open Web Text)

Max Activating Token Index: 673

Text #19

Max Range: 3.9215. Min Range: -3.9215

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1350906 (Open Web Text)

Max Activating Token Index: 538