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

Dataset: Open Web Text

Neuron 925 in Layer 3

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: 3.2305. Min Range: -3.2305

Max Act: 3.2305. Min Act: -0.1700

Data Index: 1735080 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1710. Min Act: -0.1700

Data Index: 7752873 (Open Web Text)

Max Activating Token Index: 575

Text #2

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1600. Min Act: -0.1700

Data Index: 2698362 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1293. Min Act: -0.1700

Data Index: 2497616 (Open Web Text)

Max Activating Token Index: 909

Text #4

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1418. Min Act: -0.1700

Data Index: 533427 (Open Web Text)

Max Activating Token Index: 854

Text #5

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1237. Min Act: -0.1700

Data Index: 2198415 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1317. Min Act: -0.1700

Data Index: 536963 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1072. Min Act: -0.1700

Data Index: 8603054 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0933. Min Act: -0.1700

Data Index: 211466 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0935. Min Act: -0.1700

Data Index: 1405387 (Open Web Text)

Max Activating Token Index: 496

Text #10

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.1060. Min Act: -0.1700

Data Index: 2846195 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0666. Min Act: -0.1700

Data Index: 6204636 (Open Web Text)

Max Activating Token Index: 878

Text #12

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0235. Min Act: -0.1700

Data Index: 72988 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0911. Min Act: -0.1700

Data Index: 6157464 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0941. Min Act: -0.1700

Data Index: 6536055 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0651. Min Act: -0.1700

Data Index: 6611758 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0857. Min Act: -0.1700

Data Index: 5731314 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0944. Min Act: -0.1700

Data Index: 67602 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0768. Min Act: -0.1700

Data Index: 7422207 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 3.2305. Min Range: -3.2305

Max Act: 3.0666. Min Act: -0.1700

Data Index: 8292508 (Open Web Text)

Max Activating Token Index: 1001