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

Dataset: Open Web Text

Neuron 1383 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: 3.6169. Min Range: -3.6169

Max Act: 3.6043. Min Act: -0.1700

Data Index: 1608721 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.6169. Min Act: -0.1700

Data Index: 4467729 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5978. Min Act: -0.1700

Data Index: 451198 (Open Web Text)

Max Activating Token Index: 356

Text #3

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.6084. Min Act: -0.1700

Data Index: 5263698 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5951. Min Act: -0.1700

Data Index: 1887158 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5801. Min Act: -0.1700

Data Index: 5745319 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5898. Min Act: -0.1700

Data Index: 3484672 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5984. Min Act: -0.1700

Data Index: 6119475 (Open Web Text)

Max Activating Token Index: 970

Text #8

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5780. Min Act: -0.1700

Data Index: 5611243 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5710. Min Act: -0.1700

Data Index: 6840030 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5668. Min Act: -0.1700

Data Index: 7922334 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5491. Min Act: -0.1700

Data Index: 2417480 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5191. Min Act: -0.1700

Data Index: 537142 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5446. Min Act: -0.1700

Data Index: 6651323 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5324. Min Act: -0.1700

Data Index: 3908103 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5286. Min Act: -0.1700

Data Index: 3738702 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5278. Min Act: -0.1700

Data Index: 1753278 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5489. Min Act: -0.1700

Data Index: 6733415 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5347. Min Act: -0.1700

Data Index: 5504296 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 3.6169. Min Range: -3.6169

Max Act: 3.5198. Min Act: -0.1700

Data Index: 5113119 (Open Web Text)

Max Activating Token Index: 255