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

Dataset: Open Web Text

Neuron 3008 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: 4.3868. Min Range: -4.3868

Max Act: 4.3868. Min Act: -0.1700

Data Index: 2907991 (Open Web Text)

Max Activating Token Index: 541

Text #1

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2615. Min Act: -0.1700

Data Index: 21100 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2418. Min Act: -0.1700

Data Index: 5886985 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2630. Min Act: -0.1700

Data Index: 6684396 (Open Web Text)

Max Activating Token Index: 335

Text #4

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2621. Min Act: -0.1700

Data Index: 3502937 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2079. Min Act: -0.1700

Data Index: 1409665 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2209. Min Act: -0.1700

Data Index: 6601788 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2028. Min Act: -0.1700

Data Index: 7347803 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1786. Min Act: -0.1700

Data Index: 5231923 (Open Web Text)

Max Activating Token Index: 620

Text #9

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1587. Min Act: -0.1700

Data Index: 3447486 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1591. Min Act: -0.1700

Data Index: 58113 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1895. Min Act: -0.1700

Data Index: 2289039 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1604. Min Act: -0.1700

Data Index: 1349648 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1462. Min Act: -0.1700

Data Index: 7364050 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1548. Min Act: -0.1700

Data Index: 4673503 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1396. Min Act: -0.1700

Data Index: 6550296 (Open Web Text)

Max Activating Token Index: 664

Text #16

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1239. Min Act: -0.1700

Data Index: 263711 (Open Web Text)

Max Activating Token Index: 481

Text #17

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1201. Min Act: -0.1700

Data Index: 8236063 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.0785. Min Act: -0.1700

Data Index: 875441 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.0691. Min Act: -0.1700

Data Index: 7792182 (Open Web Text)

Max Activating Token Index: 51