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

Dataset: Open Web Text

Neuron 2385 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: 1.4909. Min Range: -1.4909

Max Act: 1.4909. Min Act: -0.1700

Data Index: 1383711 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4618. Min Act: -0.1700

Data Index: 4388777 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4600. Min Act: -0.1670

Data Index: 8329103 (Open Web Text)

Max Activating Token Index: 313

Text #3

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4508. Min Act: -0.1693

Data Index: 4185466 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4254. Min Act: -0.1666

Data Index: 4579437 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4259. Min Act: -0.1700

Data Index: 8439577 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4057. Min Act: -0.1700

Data Index: 4853571 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4063. Min Act: -0.1699

Data Index: 3734395 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4043. Min Act: -0.1694

Data Index: 6046076 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4065. Min Act: -0.1700

Data Index: 7653515 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.3963. Min Act: -0.1692

Data Index: 2578337 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4009. Min Act: -0.1700

Data Index: 716146 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4048. Min Act: -0.1698

Data Index: 7608968 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.3975. Min Act: -0.1700

Data Index: 6206032 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4022. Min Act: -0.1700

Data Index: 4956942 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.3995. Min Act: -0.1699

Data Index: 4938850 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.3991. Min Act: -0.1699

Data Index: 3818505 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.3930. Min Act: -0.1696

Data Index: 3784726 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.4000. Min Act: -0.1700

Data Index: 7502126 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.3852. Min Act: -0.1697

Data Index: 4336504 (Open Web Text)

Max Activating Token Index: 715