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

Dataset: Open Web Text

Neuron 1823 in Layer 2

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: 4.4692. Min Range: -4.4692

Max Act: 4.4692. Min Act: -0.1700

Data Index: 7411030 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3855. Min Act: -0.1700

Data Index: 6821873 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3970. Min Act: -0.1700

Data Index: 6928168 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3266. Min Act: -0.1700

Data Index: 6085992 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3464. Min Act: -0.1700

Data Index: 6246920 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3400. Min Act: -0.1700

Data Index: 7100510 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3376. Min Act: -0.1700

Data Index: 8703879 (Open Web Text)

Max Activating Token Index: 564

Text #7

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3135. Min Act: -0.1700

Data Index: 8218430 (Open Web Text)

Max Activating Token Index: 709

Text #8

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3164. Min Act: -0.1700

Data Index: 3849849 (Open Web Text)

Max Activating Token Index: 692

Text #9

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3103. Min Act: -0.1700

Data Index: 5492815 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3107. Min Act: -0.1700

Data Index: 2236572 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3056. Min Act: -0.1700

Data Index: 542128 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2923. Min Act: -0.1700

Data Index: 2453774 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2337. Min Act: -0.1700

Data Index: 5116017 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2667. Min Act: -0.1700

Data Index: 2115814 (Open Web Text)

Max Activating Token Index: 475

Text #15

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2930. Min Act: -0.1700

Data Index: 2099833 (Open Web Text)

Max Activating Token Index: 412

Text #16

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.3228. Min Act: -0.1700

Data Index: 5044218 (Open Web Text)

Max Activating Token Index: 973

Text #17

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2986. Min Act: -0.1700

Data Index: 4194361 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2732. Min Act: -0.1700

Data Index: 1831235 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 4.4692. Min Range: -4.4692

Max Act: 4.2558. Min Act: -0.1700

Data Index: 902783 (Open Web Text)

Max Activating Token Index: 534