Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 295 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8398. Min Act: -0.1699

Data Index: 3793002 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8398. Min Act: -0.1700

Data Index: 637592 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8085. Min Act: -0.1700

Data Index: 4485529 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8085. Min Act: -0.1700

Data Index: 8647120 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8085. Min Act: -0.1660

Data Index: 4481332 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8085. Min Act: -0.1700

Data Index: 5655795 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8085. Min Act: -0.1700

Data Index: 8315981 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7773. Min Act: -0.1700

Data Index: 6439160 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8085. Min Act: -0.1700

Data Index: 3773179 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7773. Min Act: -0.1700

Data Index: 5042626 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7773. Min Act: -0.1700

Data Index: 4481325 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7460. Min Act: -0.1700

Data Index: 621470 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 965808 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 2432124 (Open Web Text)

Max Activating Token Index: 370

Text #14

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 6439153 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 6439144 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 1899403 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.6835. Min Act: -0.1700

Data Index: 6280435 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 1357530 (Open Web Text)

Max Activating Token Index: 956

Text #19

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.6835. Min Act: -0.1700

Data Index: 3731302 (Open Web Text)

Max Activating Token Index: 48