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

Dataset: Open Web Text

Neuron 1739 in Layer 6

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: 6.5682. Min Range: -6.5682

Max Act: 6.5682. Min Act: -0.1700

Data Index: 7493663 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 6.5682. Min Range: -6.5682

Max Act: 6.3830. Min Act: -0.1700

Data Index: 6553973 (Open Web Text)

Max Activating Token Index: 575

Text #2

Max Range: 6.5682. Min Range: -6.5682

Max Act: 6.2410. Min Act: -0.1699

Data Index: 7205016 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 6.5682. Min Range: -6.5682

Max Act: 6.1700. Min Act: -0.1700

Data Index: 8541906 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 6.5682. Min Range: -6.5682

Max Act: 6.1123. Min Act: -0.1699

Data Index: 2616256 (Open Web Text)

Max Activating Token Index: 759

Text #5

Max Range: 6.5682. Min Range: -6.5682

Max Act: 6.0228. Min Act: -0.1700

Data Index: 8715756 (Open Web Text)

Max Activating Token Index: 741

Text #6

Max Range: 6.5682. Min Range: -6.5682

Max Act: 6.0260. Min Act: -0.1700

Data Index: 5554005 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.9217. Min Act: -0.1700

Data Index: 3266272 (Open Web Text)

Max Activating Token Index: 363

Text #8

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.9776. Min Act: -0.1700

Data Index: 6756076 (Open Web Text)

Max Activating Token Index: 721

Text #9

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8895. Min Act: -0.1700

Data Index: 1015903 (Open Web Text)

Max Activating Token Index: 730

Text #10

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.9427. Min Act: -0.1698

Data Index: 4338755 (Open Web Text)

Max Activating Token Index: 178

Text #11

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8712. Min Act: -0.1700

Data Index: 6348248 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8707. Min Act: -0.1700

Data Index: 6601769 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.9139. Min Act: -0.1700

Data Index: 3590347 (Open Web Text)

Max Activating Token Index: 842

Text #14

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.9285. Min Act: -0.1698

Data Index: 3636209 (Open Web Text)

Max Activating Token Index: 724

Text #15

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8656. Min Act: -0.1700

Data Index: 5574843 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.9110. Min Act: -0.1700

Data Index: 642233 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8964. Min Act: -0.1699

Data Index: 4728028 (Open Web Text)

Max Activating Token Index: 998

Text #18

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8655. Min Act: -0.1700

Data Index: 764789 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 6.5682. Min Range: -6.5682

Max Act: 5.8573. Min Act: -0.1700

Data Index: 1114990 (Open Web Text)

Max Activating Token Index: 275