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

Dataset: Open Web Text

Neuron 2236 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: 1.9599. Min Range: -1.9599

Max Act: 1.9599. Min Act: -0.1700

Data Index: 6073118 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.9278. Min Act: -0.1700

Data Index: 3201567 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.9308. Min Act: -0.1700

Data Index: 112681 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.9376. Min Act: -0.1700

Data Index: 2914524 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.9136. Min Act: -0.1700

Data Index: 6120248 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8789. Min Act: -0.1700

Data Index: 7347511 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8785. Min Act: -0.1700

Data Index: 2041560 (Open Web Text)

Max Activating Token Index: 752

Text #7

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8719. Min Act: -0.1700

Data Index: 7036398 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8484. Min Act: -0.1700

Data Index: 376486 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8224. Min Act: -0.1700

Data Index: 6090768 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8580. Min Act: -0.1700

Data Index: 8827462 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8357. Min Act: -0.1700

Data Index: 7896620 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8307. Min Act: -0.1700

Data Index: 925157 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8393. Min Act: -0.1700

Data Index: 3555238 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8441. Min Act: -0.1700

Data Index: 6675260 (Open Web Text)

Max Activating Token Index: 650

Text #15

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8219. Min Act: -0.1700

Data Index: 1734147 (Open Web Text)

Max Activating Token Index: 460

Text #16

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8283. Min Act: -0.1700

Data Index: 930433 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8126. Min Act: -0.1700

Data Index: 6854649 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8097. Min Act: -0.1700

Data Index: 2293420 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 1.9599. Min Range: -1.9599

Max Act: 1.8196. Min Act: -0.1700

Data Index: 6646565 (Open Web Text)

Max Activating Token Index: 641