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

Dataset: Open Web Text

Neuron 1589 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: 6.0422. Min Range: -6.0422

Max Act: 6.0422. Min Act: -0.1700

Data Index: 5418046 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9712. Min Act: -0.1700

Data Index: 3626345 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9780. Min Act: -0.1700

Data Index: 1075817 (Open Web Text)

Max Activating Token Index: 992

Text #3

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9554. Min Act: -0.1700

Data Index: 5976813 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9636. Min Act: -0.1700

Data Index: 3482145 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9525. Min Act: -0.1700

Data Index: 6965575 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9264. Min Act: -0.1700

Data Index: 6983872 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9172. Min Act: -0.1700

Data Index: 3596438 (Open Web Text)

Max Activating Token Index: 232

Text #8

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9206. Min Act: -0.1700

Data Index: 3983934 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9055. Min Act: -0.1700

Data Index: 3803474 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8997. Min Act: -0.1700

Data Index: 8482463 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9352. Min Act: -0.1700

Data Index: 7426201 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9191. Min Act: -0.1700

Data Index: 6223543 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8906. Min Act: -0.1700

Data Index: 504943 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8851. Min Act: -0.1700

Data Index: 4005758 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8673. Min Act: -0.1700

Data Index: 732763 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.9059. Min Act: -0.1700

Data Index: 7742574 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8914. Min Act: -0.1700

Data Index: 5607612 (Open Web Text)

Max Activating Token Index: 587

Text #18

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8683. Min Act: -0.1700

Data Index: 4812464 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 6.0422. Min Range: -6.0422

Max Act: 5.8192. Min Act: -0.1700

Data Index: 1560939 (Open Web Text)

Max Activating Token Index: 739