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

Dataset: Open Web Text

Neuron 1314 in Layer 0

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: 1.6145. Min Range: -1.6145

Max Act: 1.6145. Min Act: -0.1690

Data Index: 1191676 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.6030. Min Act: -0.1654

Data Index: 3726220 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5962. Min Act: -0.1589

Data Index: 5021295 (Open Web Text)

Max Activating Token Index: 108

Text #3

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5783. Min Act: -0.1556

Data Index: 6893977 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5851. Min Act: -0.1685

Data Index: 2921632 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5786. Min Act: -0.1553

Data Index: 2362672 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5703. Min Act: -0.1572

Data Index: 3648392 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5799. Min Act: -0.1696

Data Index: 5075957 (Open Web Text)

Max Activating Token Index: 65

Text #8

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5812. Min Act: -0.1664

Data Index: 1380574 (Open Web Text)

Max Activating Token Index: 526

Text #9

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5756. Min Act: -0.1697

Data Index: 7101623 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5756. Min Act: -0.1606

Data Index: 4338323 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5700. Min Act: -0.1651

Data Index: 1619921 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5698. Min Act: -0.1698

Data Index: 5615141 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5682. Min Act: -0.1585

Data Index: 7127977 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5668. Min Act: -0.1579

Data Index: 4198890 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5603. Min Act: -0.1587

Data Index: 445895 (Open Web Text)

Max Activating Token Index: 260

Text #16

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5683. Min Act: -0.1700

Data Index: 4937368 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5660. Min Act: -0.1678

Data Index: 6433596 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5741. Min Act: -0.1700

Data Index: 3749916 (Open Web Text)

Max Activating Token Index: 768

Text #19

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5607. Min Act: -0.1667

Data Index: 4408023 (Open Web Text)

Max Activating Token Index: 622