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

Dataset: Open Web Text

Neuron 2621 in Layer 0

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: 1.8879. Min Range: -1.8879

Max Act: 1.8879. Min Act: -0.1698

Data Index: 5356255 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8640. Min Act: -0.1700

Data Index: 1946265 (Open Web Text)

Max Activating Token Index: 857

Text #2

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8601. Min Act: -0.1693

Data Index: 2205283 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8651. Min Act: -0.1689

Data Index: 7711028 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8540. Min Act: -0.1654

Data Index: 8092963 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8406. Min Act: -0.1700

Data Index: 2529717 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8389. Min Act: -0.1696

Data Index: 2726978 (Open Web Text)

Max Activating Token Index: 632

Text #7

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8466. Min Act: -0.1693

Data Index: 4004253 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8361. Min Act: -0.1700

Data Index: 8544050 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8289. Min Act: -0.1700

Data Index: 2130362 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8198. Min Act: -0.1697

Data Index: 6164170 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8264. Min Act: -0.1697

Data Index: 3131804 (Open Web Text)

Max Activating Token Index: 487

Text #12

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8264. Min Act: -0.1697

Data Index: 4517302 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8153. Min Act: -0.1695

Data Index: 2079489 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8169. Min Act: -0.1674

Data Index: 6820404 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8250. Min Act: -0.1667

Data Index: 2328216 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8175. Min Act: -0.1688

Data Index: 735405 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8194. Min Act: -0.1698

Data Index: 1721493 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8144. Min Act: -0.1694

Data Index: 7751262 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.8139. Min Act: -0.1700

Data Index: 3282611 (Open Web Text)

Max Activating Token Index: 1000