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

Dataset: Open Web Text

Neuron 955 in Layer 4

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: 1.1965. Min Range: -1.1965

Max Act: 1.1839. Min Act: -0.1668

Data Index: 6568786 (Open Web Text)

Max Activating Token Index: 560

Text #1

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1965. Min Act: -0.1684

Data Index: 2606046 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1644. Min Act: -0.1586

Data Index: 4870392 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1450. Min Act: -0.1693

Data Index: 2774181 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1589. Min Act: -0.1700

Data Index: 3721425 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1348. Min Act: -0.1699

Data Index: 5468256 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1255. Min Act: -0.1700

Data Index: 64822 (Open Web Text)

Max Activating Token Index: 445

Text #7

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1297. Min Act: -0.1696

Data Index: 29704 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1212. Min Act: -0.1358

Data Index: 7253638 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1075. Min Act: -0.1695

Data Index: 6618716 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1051. Min Act: -0.1698

Data Index: 3744452 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1146. Min Act: -0.1630

Data Index: 2559768 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1203. Min Act: -0.1698

Data Index: 5683362 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1073. Min Act: -0.1692

Data Index: 8049381 (Open Web Text)

Max Activating Token Index: 504

Text #14

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1179. Min Act: -0.1691

Data Index: 6357876 (Open Web Text)

Max Activating Token Index: 335

Text #15

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1005. Min Act: -0.1668

Data Index: 6187341 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.0996. Min Act: -0.1608

Data Index: 2559767 (Open Web Text)

Max Activating Token Index: 543

Text #17

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.0971. Min Act: -0.1695

Data Index: 6735157 (Open Web Text)

Max Activating Token Index: 610

Text #18

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.0905. Min Act: -0.1691

Data Index: 7000636 (Open Web Text)

Max Activating Token Index: 547

Text #19

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.0856. Min Act: -0.1690

Data Index: 4271282 (Open Web Text)

Max Activating Token Index: 573