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

Dataset: Open Web Text

Neuron 1933 in Layer 2

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: 3.6085. Min Range: -3.6085

Max Act: 3.6052. Min Act: -0.1700

Data Index: 8633050 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.6085. Min Act: -0.1700

Data Index: 3121233 (Open Web Text)

Max Activating Token Index: 742

Text #2

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5968. Min Act: -0.1700

Data Index: 7617856 (Open Web Text)

Max Activating Token Index: 392

Text #3

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5913. Min Act: -0.1700

Data Index: 3012430 (Open Web Text)

Max Activating Token Index: 985

Text #4

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5816. Min Act: -0.1700

Data Index: 6873119 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5904. Min Act: -0.1700

Data Index: 7481230 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5612. Min Act: -0.1700

Data Index: 3685576 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5441. Min Act: -0.1700

Data Index: 2675795 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5613. Min Act: -0.1700

Data Index: 2565876 (Open Web Text)

Max Activating Token Index: 825

Text #9

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5579. Min Act: -0.1700

Data Index: 948640 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5368. Min Act: -0.1700

Data Index: 2687949 (Open Web Text)

Max Activating Token Index: 414

Text #11

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5421. Min Act: -0.1700

Data Index: 1347203 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5256. Min Act: -0.1700

Data Index: 4668945 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5309. Min Act: -0.1700

Data Index: 3066350 (Open Web Text)

Max Activating Token Index: 431

Text #14

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5448. Min Act: -0.1700

Data Index: 2027525 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5171. Min Act: -0.1700

Data Index: 7576510 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5051. Min Act: -0.1700

Data Index: 1440190 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5274. Min Act: -0.1700

Data Index: 226983 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5265. Min Act: -0.1700

Data Index: 1415077 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 3.6085. Min Range: -3.6085

Max Act: 3.5261. Min Act: -0.1700

Data Index: 6876324 (Open Web Text)

Max Activating Token Index: 324