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

Dataset: Open Web Text

Neuron 1426 in Layer 5

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: 5.2725. Min Range: -5.2725

Max Act: 5.2517. Min Act: -0.1700

Data Index: 2387827 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 5.2725. Min Range: -5.2725

Max Act: 5.2725. Min Act: -0.1700

Data Index: 8588400 (Open Web Text)

Max Activating Token Index: 755

Text #2

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8896. Min Act: -0.1700

Data Index: 3182242 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8604. Min Act: -0.1700

Data Index: 1911416 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8717. Min Act: -0.1700

Data Index: 5703700 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8383. Min Act: -0.1700

Data Index: 3762860 (Open Web Text)

Max Activating Token Index: 848

Text #6

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7705. Min Act: -0.1700

Data Index: 159403 (Open Web Text)

Max Activating Token Index: 390

Text #7

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8081. Min Act: -0.1700

Data Index: 4653660 (Open Web Text)

Max Activating Token Index: 782

Text #8

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7646. Min Act: -0.1700

Data Index: 159401 (Open Web Text)

Max Activating Token Index: 209

Text #9

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7475. Min Act: -0.1700

Data Index: 1131255 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7599. Min Act: -0.1700

Data Index: 2977070 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7266. Min Act: -0.1700

Data Index: 4278490 (Open Web Text)

Max Activating Token Index: 250

Text #12

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6408. Min Act: -0.1700

Data Index: 1830730 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6992. Min Act: -0.1700

Data Index: 275801 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6776. Min Act: -0.1700

Data Index: 6962075 (Open Web Text)

Max Activating Token Index: 200

Text #15

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6718. Min Act: -0.1700

Data Index: 3565407 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7093. Min Act: -0.1700

Data Index: 6562245 (Open Web Text)

Max Activating Token Index: 709

Text #17

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6780. Min Act: -0.1700

Data Index: 3823390 (Open Web Text)

Max Activating Token Index: 497

Text #18

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6859. Min Act: -0.1700

Data Index: 1219306 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7203. Min Act: -0.1700

Data Index: 2698366 (Open Web Text)

Max Activating Token Index: 725