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

Dataset: Open Web Text

Neuron 534 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: 4.4864. Min Range: -4.4864

Max Act: 4.4864. Min Act: -0.1700

Data Index: 1177989 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2982. Min Act: -0.1700

Data Index: 6331720 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2751. Min Act: -0.1700

Data Index: 8762791 (Open Web Text)

Max Activating Token Index: 758

Text #3

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2648. Min Act: -0.1700

Data Index: 6438503 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2389. Min Act: -0.1700

Data Index: 7919807 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2298. Min Act: -0.1700

Data Index: 6796434 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1984. Min Act: -0.1700

Data Index: 5286254 (Open Web Text)

Max Activating Token Index: 867

Text #7

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2079. Min Act: -0.1700

Data Index: 7708733 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1907. Min Act: -0.1700

Data Index: 4235097 (Open Web Text)

Max Activating Token Index: 828

Text #9

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1912. Min Act: -0.1700

Data Index: 2110971 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2030. Min Act: -0.1700

Data Index: 3022902 (Open Web Text)

Max Activating Token Index: 687

Text #11

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1506. Min Act: -0.1700

Data Index: 1324251 (Open Web Text)

Max Activating Token Index: 756

Text #12

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1841. Min Act: -0.1700

Data Index: 2690400 (Open Web Text)

Max Activating Token Index: 704

Text #13

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1341. Min Act: -0.1700

Data Index: 1757368 (Open Web Text)

Max Activating Token Index: 606

Text #14

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1588. Min Act: -0.1700

Data Index: 95585 (Open Web Text)

Max Activating Token Index: 795

Text #15

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1559. Min Act: -0.1700

Data Index: 8117855 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1497. Min Act: -0.1700

Data Index: 6571724 (Open Web Text)

Max Activating Token Index: 49

Text #17

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1392. Min Act: -0.1700

Data Index: 2562251 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1456. Min Act: -0.1700

Data Index: 3074380 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.1308. Min Act: -0.1700

Data Index: 153854 (Open Web Text)

Max Activating Token Index: 972