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

Dataset: Open Web Text

Neuron 1916 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: 4.4219. Min Range: -4.4219

Max Act: 4.4219. Min Act: -0.1700

Data Index: 4572714 (Open Web Text)

Max Activating Token Index: 865

Text #1

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.4054. Min Act: -0.1700

Data Index: 4572713 (Open Web Text)

Max Activating Token Index: 158

Text #2

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.3227. Min Act: -0.1700

Data Index: 4497774 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.1995. Min Act: -0.1700

Data Index: 2948712 (Open Web Text)

Max Activating Token Index: 1005

Text #4

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.1508. Min Act: -0.1700

Data Index: 6531177 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.1313. Min Act: -0.1700

Data Index: 4240907 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.1039. Min Act: -0.1700

Data Index: 6126779 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.0500. Min Act: -0.1700

Data Index: 171376 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.0188. Min Act: -0.1700

Data Index: 3100017 (Open Web Text)

Max Activating Token Index: 870

Text #9

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.0291. Min Act: -0.1700

Data Index: 2846653 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.0014. Min Act: -0.1700

Data Index: 1713108 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.0471. Min Act: -0.1700

Data Index: 6034126 (Open Web Text)

Max Activating Token Index: 745

Text #12

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9907. Min Act: -0.1700

Data Index: 3696054 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 4.4219. Min Range: -4.4219

Max Act: 4.0309. Min Act: -0.1700

Data Index: 4930005 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9898. Min Act: -0.1700

Data Index: 1992751 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9509. Min Act: -0.1700

Data Index: 164666 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9820. Min Act: -0.1700

Data Index: 70141 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9558. Min Act: -0.1700

Data Index: 537872 (Open Web Text)

Max Activating Token Index: 738

Text #18

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9414. Min Act: -0.1700

Data Index: 524362 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 4.4219. Min Range: -4.4219

Max Act: 3.9372. Min Act: -0.1700

Data Index: 1558969 (Open Web Text)

Max Activating Token Index: 724