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

Dataset: Open Web Text

Neuron 2237 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: 1.9211. Min Range: -1.9211

Max Act: 1.9211. Min Act: -0.1700

Data Index: 6331978 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8715. Min Act: -0.1700

Data Index: 2811059 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8624. Min Act: -0.1700

Data Index: 7027111 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8610. Min Act: -0.1700

Data Index: 1219722 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8499. Min Act: -0.1700

Data Index: 6961342 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8309. Min Act: -0.1700

Data Index: 2716820 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8343. Min Act: -0.1700

Data Index: 464481 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8231. Min Act: -0.1700

Data Index: 4737506 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8209. Min Act: -0.1700

Data Index: 4789290 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8217. Min Act: -0.1700

Data Index: 5419972 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8047. Min Act: -0.1700

Data Index: 8716493 (Open Web Text)

Max Activating Token Index: 96

Text #11

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8065. Min Act: -0.1700

Data Index: 1096777 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8330. Min Act: -0.1700

Data Index: 4108590 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7903. Min Act: -0.1700

Data Index: 510695 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7731. Min Act: -0.1700

Data Index: 1587044 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7881. Min Act: -0.1700

Data Index: 6775466 (Open Web Text)

Max Activating Token Index: 657

Text #16

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7866. Min Act: -0.1700

Data Index: 556556 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7715. Min Act: -0.1700

Data Index: 1325504 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7722. Min Act: -0.1700

Data Index: 899442 (Open Web Text)

Max Activating Token Index: 348

Text #19

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7651. Min Act: -0.1700

Data Index: 2113183 (Open Web Text)

Max Activating Token Index: 243