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

Dataset: Open Web Text

Neuron 2631 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: 5.7139. Min Range: -5.7139

Max Act: 5.7139. Min Act: -0.1700

Data Index: 1741897 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.5225. Min Act: -0.1700

Data Index: 3860551 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.5192. Min Act: -0.1700

Data Index: 5609930 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.3992. Min Act: -0.1700

Data Index: 4642282 (Open Web Text)

Max Activating Token Index: 434

Text #4

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.3326. Min Act: -0.1700

Data Index: 1034765 (Open Web Text)

Max Activating Token Index: 230

Text #5

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2686. Min Act: -0.1700

Data Index: 376080 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.3056. Min Act: -0.1700

Data Index: 1884335 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2767. Min Act: -0.1700

Data Index: 6052891 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.3016. Min Act: -0.1700

Data Index: 5874754 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2761. Min Act: -0.1700

Data Index: 3509314 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2794. Min Act: -0.1700

Data Index: 2912732 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2474. Min Act: -0.1700

Data Index: 3613074 (Open Web Text)

Max Activating Token Index: 117

Text #12

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2530. Min Act: -0.1700

Data Index: 8401360 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2665. Min Act: -0.1700

Data Index: 7295090 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2711. Min Act: -0.1700

Data Index: 142228 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2540. Min Act: -0.1700

Data Index: 257921 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.1877. Min Act: -0.1700

Data Index: 1732401 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.1788. Min Act: -0.1700

Data Index: 4934688 (Open Web Text)

Max Activating Token Index: 740

Text #18

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.1941. Min Act: -0.1700

Data Index: 294267 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 5.7139. Min Range: -5.7139

Max Act: 5.2357. Min Act: -0.1700

Data Index: 1980394 (Open Web Text)

Max Activating Token Index: 153