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

Dataset: Open Web Text

Neuron 530 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: 3.9889. Min Range: -3.9889

Max Act: 3.9889. Min Act: -0.1700

Data Index: 7170916 (Open Web Text)

Max Activating Token Index: 333

Text #1

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9781. Min Act: -0.1700

Data Index: 2629309 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9604. Min Act: -0.1700

Data Index: 8146025 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9743. Min Act: -0.1700

Data Index: 2956608 (Open Web Text)

Max Activating Token Index: 817

Text #4

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9480. Min Act: -0.1700

Data Index: 8441985 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9665. Min Act: -0.1700

Data Index: 1668961 (Open Web Text)

Max Activating Token Index: 243

Text #6

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9193. Min Act: -0.1700

Data Index: 423009 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9204. Min Act: -0.1700

Data Index: 1706523 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9138. Min Act: -0.1700

Data Index: 8370534 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8835. Min Act: -0.1700

Data Index: 6492200 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9297. Min Act: -0.1700

Data Index: 8657053 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8628. Min Act: -0.1700

Data Index: 5271756 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8934. Min Act: -0.1700

Data Index: 4481218 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8932. Min Act: -0.1700

Data Index: 4228982 (Open Web Text)

Max Activating Token Index: 606

Text #14

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8884. Min Act: -0.1700

Data Index: 7720721 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8852. Min Act: -0.1700

Data Index: 4033552 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8603. Min Act: -0.1700

Data Index: 6608868 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8421. Min Act: -0.1700

Data Index: 397090 (Open Web Text)

Max Activating Token Index: 156

Text #18

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8834. Min Act: -0.1700

Data Index: 462294 (Open Web Text)

Max Activating Token Index: 903

Text #19

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8108. Min Act: -0.1700

Data Index: 2112769 (Open Web Text)

Max Activating Token Index: 211