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

Dataset: Open Web Text

Neuron 481 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: 4.4099. Min Range: -4.4099

Max Act: 4.4099. Min Act: -0.1700

Data Index: 6424014 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.3282. Min Act: -0.1700

Data Index: 1049673 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2651. Min Act: -0.1700

Data Index: 1421270 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2937. Min Act: -0.1700

Data Index: 5845146 (Open Web Text)

Max Activating Token Index: 688

Text #4

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2330. Min Act: -0.1700

Data Index: 1579416 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2171. Min Act: -0.1700

Data Index: 6665941 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2242. Min Act: -0.1700

Data Index: 1585761 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2047. Min Act: -0.1700

Data Index: 4092731 (Open Web Text)

Max Activating Token Index: 291

Text #8

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.2240. Min Act: -0.1700

Data Index: 3240275 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1686. Min Act: -0.1700

Data Index: 4663965 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1673. Min Act: -0.1700

Data Index: 1820705 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1502. Min Act: -0.1700

Data Index: 401579 (Open Web Text)

Max Activating Token Index: 749

Text #12

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1557. Min Act: -0.1700

Data Index: 35711 (Open Web Text)

Max Activating Token Index: 805

Text #13

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1634. Min Act: -0.1700

Data Index: 6365686 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1535. Min Act: -0.1700

Data Index: 4713627 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1563. Min Act: -0.1700

Data Index: 2646680 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1201. Min Act: -0.1700

Data Index: 4447586 (Open Web Text)

Max Activating Token Index: 682

Text #17

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1404. Min Act: -0.1700

Data Index: 3023230 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1343. Min Act: -0.1700

Data Index: 4588231 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 4.4099. Min Range: -4.4099

Max Act: 4.1291. Min Act: -0.1700

Data Index: 1980959 (Open Web Text)

Max Activating Token Index: 195