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

Dataset: Open Web Text

Neuron 1451 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: 4.3277. Min Range: -4.3277

Max Act: 4.3277. Min Act: -0.1700

Data Index: 2948986 (Open Web Text)

Max Activating Token Index: 353

Text #1

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.2289. Min Act: -0.1700

Data Index: 3139652 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.1779. Min Act: -0.1700

Data Index: 1416880 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.1081. Min Act: -0.1700

Data Index: 1479251 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.0790. Min Act: -0.1700

Data Index: 624901 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.0651. Min Act: -0.1700

Data Index: 574275 (Open Web Text)

Max Activating Token Index: 816

Text #6

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.0361. Min Act: -0.1700

Data Index: 3809406 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.0516. Min Act: -0.1700

Data Index: 383908 (Open Web Text)

Max Activating Token Index: 816

Text #8

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.0043. Min Act: -0.1700

Data Index: 1643692 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 4.3277. Min Range: -4.3277

Max Act: 4.0090. Min Act: -0.1700

Data Index: 4888560 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9794. Min Act: -0.1700

Data Index: 3764280 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9816. Min Act: -0.1700

Data Index: 5778629 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9573. Min Act: -0.1700

Data Index: 680886 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9663. Min Act: -0.1700

Data Index: 6794086 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9276. Min Act: -0.1700

Data Index: 2717765 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9320. Min Act: -0.1700

Data Index: 3516779 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9351. Min Act: -0.1700

Data Index: 8605306 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9144. Min Act: -0.1700

Data Index: 5492903 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.9135. Min Act: -0.1700

Data Index: 3045796 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 4.3277. Min Range: -4.3277

Max Act: 3.8954. Min Act: -0.1700

Data Index: 2841675 (Open Web Text)

Max Activating Token Index: 650