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

Dataset: Open Web Text

Neuron 372 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: 3.8704. Min Range: -3.8704

Max Act: 3.8486. Min Act: -0.1700

Data Index: 2526132 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8545. Min Act: -0.1700

Data Index: 3923286 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8607. Min Act: -0.1700

Data Index: 3117236 (Open Web Text)

Max Activating Token Index: 504

Text #3

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8554. Min Act: -0.1700

Data Index: 1623008 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8634. Min Act: -0.1700

Data Index: 5044771 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8704. Min Act: -0.1700

Data Index: 7080732 (Open Web Text)

Max Activating Token Index: 454

Text #6

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8417. Min Act: -0.1700

Data Index: 7745455 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8267. Min Act: -0.1700

Data Index: 1793576 (Open Web Text)

Max Activating Token Index: 470

Text #8

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8361. Min Act: -0.1700

Data Index: 8403814 (Open Web Text)

Max Activating Token Index: 709

Text #9

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8373. Min Act: -0.1700

Data Index: 3900740 (Open Web Text)

Max Activating Token Index: 974

Text #10

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8156. Min Act: -0.1700

Data Index: 1604159 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8240. Min Act: -0.1700

Data Index: 2098931 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8361. Min Act: -0.1700

Data Index: 6495600 (Open Web Text)

Max Activating Token Index: 607

Text #13

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8522. Min Act: -0.1700

Data Index: 5181764 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8308. Min Act: -0.1700

Data Index: 3978434 (Open Web Text)

Max Activating Token Index: 703

Text #15

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8432. Min Act: -0.1700

Data Index: 2223209 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.7917. Min Act: -0.1700

Data Index: 311316 (Open Web Text)

Max Activating Token Index: 838

Text #17

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.7878. Min Act: -0.1700

Data Index: 832339 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8020. Min Act: -0.1700

Data Index: 1622015 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8150. Min Act: -0.1700

Data Index: 898013 (Open Web Text)

Max Activating Token Index: 350