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

Dataset: Open Web Text

Neuron 93 in Layer 4

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: 4.2851. Min Range: -4.2851

Max Act: 4.2577. Min Act: -0.1700

Data Index: 6214731 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.2851. Min Act: -0.1700

Data Index: 5051980 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.2775. Min Act: -0.1700

Data Index: 4421529 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.2716. Min Act: -0.1700

Data Index: 4036050 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.2404. Min Act: -0.1700

Data Index: 4783816 (Open Web Text)

Max Activating Token Index: 803

Text #5

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.2040. Min Act: -0.1700

Data Index: 180803 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1577. Min Act: -0.1700

Data Index: 3669825 (Open Web Text)

Max Activating Token Index: 154

Text #7

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1777. Min Act: -0.1700

Data Index: 254099 (Open Web Text)

Max Activating Token Index: 294

Text #8

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1500. Min Act: -0.1700

Data Index: 4123417 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1408. Min Act: -0.1700

Data Index: 520819 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1193. Min Act: -0.1700

Data Index: 296306 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1690. Min Act: -0.1700

Data Index: 5613331 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0786. Min Act: -0.1700

Data Index: 468702 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1121. Min Act: -0.1700

Data Index: 1050819 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0828. Min Act: -0.1700

Data Index: 1033757 (Open Web Text)

Max Activating Token Index: 428

Text #15

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0544. Min Act: -0.1700

Data Index: 2526282 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.1112. Min Act: -0.1700

Data Index: 2048957 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0419. Min Act: -0.1700

Data Index: 6231215 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0222. Min Act: -0.1700

Data Index: 1096450 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0350. Min Act: -0.1700

Data Index: 3769574 (Open Web Text)

Max Activating Token Index: 770