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

Dataset: Open Web Text

Neuron 1909 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: 2.2702. Min Range: -2.2702

Max Act: 2.2702. Min Act: -0.1700

Data Index: 5181169 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2438. Min Act: -0.1700

Data Index: 5069120 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2527. Min Act: -0.1700

Data Index: 5864509 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2432. Min Act: -0.1700

Data Index: 1940771 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2316. Min Act: -0.1700

Data Index: 4905468 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2378. Min Act: -0.1700

Data Index: 2521913 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2230. Min Act: -0.1700

Data Index: 4473415 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1907. Min Act: -0.1700

Data Index: 4335242 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.2000. Min Act: -0.1698

Data Index: 4441503 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1993. Min Act: -0.1700

Data Index: 4341816 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1999. Min Act: -0.1700

Data Index: 4124047 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1958. Min Act: -0.1700

Data Index: 8464040 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1966. Min Act: -0.1700

Data Index: 8618479 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1964. Min Act: -0.1700

Data Index: 1367818 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1760. Min Act: -0.1700

Data Index: 5203762 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1799. Min Act: -0.1700

Data Index: 794170 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1761. Min Act: -0.1699

Data Index: 4068368 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1759. Min Act: -0.1700

Data Index: 2409602 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1765. Min Act: -0.1700

Data Index: 5402090 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.1761. Min Act: -0.1700

Data Index: 5632734 (Open Web Text)

Max Activating Token Index: 3