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

Dataset: Open Web Text

Neuron 993 in Layer 5

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: 3.7047. Min Range: -3.7047

Max Act: 3.7047. Min Act: -0.1700

Data Index: 6608440 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.6901. Min Act: -0.1700

Data Index: 7898878 (Open Web Text)

Max Activating Token Index: 698

Text #2

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.6569. Min Act: -0.1700

Data Index: 5529253 (Open Web Text)

Max Activating Token Index: 781

Text #3

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.6014. Min Act: -0.1700

Data Index: 4818764 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.6046. Min Act: -0.1700

Data Index: 5901021 (Open Web Text)

Max Activating Token Index: 252

Text #5

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5641. Min Act: -0.1700

Data Index: 4846124 (Open Web Text)

Max Activating Token Index: 822

Text #6

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4814. Min Act: -0.1700

Data Index: 3964282 (Open Web Text)

Max Activating Token Index: 627

Text #7

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4994. Min Act: -0.1700

Data Index: 1263683 (Open Web Text)

Max Activating Token Index: 450

Text #8

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4908. Min Act: -0.1700

Data Index: 3212344 (Open Web Text)

Max Activating Token Index: 1001

Text #9

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.5113. Min Act: -0.1700

Data Index: 7526196 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4502. Min Act: -0.1700

Data Index: 6554481 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4789. Min Act: -0.1700

Data Index: 353610 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4806. Min Act: -0.1700

Data Index: 53121 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4378. Min Act: -0.1700

Data Index: 6890925 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1420389 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4422. Min Act: -0.1700

Data Index: 5841763 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4356. Min Act: -0.1700

Data Index: 4970253 (Open Web Text)

Max Activating Token Index: 847

Text #17

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4389. Min Act: -0.1700

Data Index: 8058815 (Open Web Text)

Max Activating Token Index: 819

Text #18

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4250. Min Act: -0.1700

Data Index: 7085774 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 3.7047. Min Range: -3.7047

Max Act: 3.4351. Min Act: -0.1700

Data Index: 1770638 (Open Web Text)

Max Activating Token Index: 109