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

Dataset: Open Web Text

Neuron 635 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: 5.5878. Min Range: -5.5878

Max Act: 5.5878. Min Act: -0.1700

Data Index: 2021778 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.5665. Min Act: -0.1700

Data Index: 1810440 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.3416. Min Act: -0.1700

Data Index: 6387360 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.2352. Min Act: -0.1700

Data Index: 6881475 (Open Web Text)

Max Activating Token Index: 724

Text #4

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.2102. Min Act: -0.1700

Data Index: 4134355 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1782. Min Act: -0.1700

Data Index: 3838596 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1779. Min Act: -0.1700

Data Index: 420258 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1288. Min Act: -0.1699

Data Index: 5982425 (Open Web Text)

Max Activating Token Index: 447

Text #8

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1576. Min Act: -0.1700

Data Index: 7709272 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1327. Min Act: -0.1700

Data Index: 4056722 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1419. Min Act: -0.1700

Data Index: 6881372 (Open Web Text)

Max Activating Token Index: 458

Text #11

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.1156. Min Act: -0.1700

Data Index: 8711412 (Open Web Text)

Max Activating Token Index: 195

Text #12

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0669. Min Act: -0.1700

Data Index: 209988 (Open Web Text)

Max Activating Token Index: 722

Text #13

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0604. Min Act: -0.1700

Data Index: 3279231 (Open Web Text)

Max Activating Token Index: 892

Text #14

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0805. Min Act: -0.1700

Data Index: 5649113 (Open Web Text)

Max Activating Token Index: 401

Text #15

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0990. Min Act: -0.1700

Data Index: 3155364 (Open Web Text)

Max Activating Token Index: 210

Text #16

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0859. Min Act: -0.1700

Data Index: 6921480 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0866. Min Act: -0.1700

Data Index: 3438412 (Open Web Text)

Max Activating Token Index: 925

Text #18

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0955. Min Act: -0.1700

Data Index: 2973524 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 5.5878. Min Range: -5.5878

Max Act: 5.0904. Min Act: -0.1700

Data Index: 2778552 (Open Web Text)

Max Activating Token Index: 935