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

Dataset: Open Web Text

Neuron 1814 in Layer 1

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: 1.6206. Min Range: -1.6206

Max Act: 1.6206. Min Act: -0.1700

Data Index: 6789025 (Open Web Text)

Max Activating Token Index: 809

Text #1

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.6034. Min Act: -0.1700

Data Index: 3210994 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5874. Min Act: -0.1690

Data Index: 3297112 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5832. Min Act: -0.1700

Data Index: 3024669 (Open Web Text)

Max Activating Token Index: 863

Text #4

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5645. Min Act: -0.1700

Data Index: 731298 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5517. Min Act: -0.1700

Data Index: 6199588 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5671. Min Act: -0.1700

Data Index: 1320096 (Open Web Text)

Max Activating Token Index: 581

Text #7

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5525. Min Act: -0.1694

Data Index: 6558593 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5628. Min Act: -0.1694

Data Index: 3088178 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5637. Min Act: -0.1700

Data Index: 8206864 (Open Web Text)

Max Activating Token Index: 375

Text #10

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5592. Min Act: -0.1700

Data Index: 4311103 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5590. Min Act: -0.1700

Data Index: 6882986 (Open Web Text)

Max Activating Token Index: 791

Text #12

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5473. Min Act: -0.1695

Data Index: 2327812 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5536. Min Act: -0.1698

Data Index: 4630538 (Open Web Text)

Max Activating Token Index: 905

Text #14

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5450. Min Act: -0.1700

Data Index: 7835724 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5426. Min Act: -0.1700

Data Index: 7036686 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5451. Min Act: -0.1700

Data Index: 1590551 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5494. Min Act: -0.1697

Data Index: 2019777 (Open Web Text)

Max Activating Token Index: 895

Text #18

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5547. Min Act: -0.1700

Data Index: 396201 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5293. Min Act: -0.1696

Data Index: 1158077 (Open Web Text)

Max Activating Token Index: 866