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

Dataset: Open Web Text

Neuron 885 in Layer 1

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: 1.6005. Min Range: -1.6005

Max Act: 1.6005. Min Act: -0.1700

Data Index: 4505398 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4772. Min Act: -0.1700

Data Index: 2510679 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4696. Min Act: -0.1700

Data Index: 937442 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4696. Min Act: -0.1700

Data Index: 401621 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4621. Min Act: -0.1694

Data Index: 317673 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4433. Min Act: -0.1700

Data Index: 1893178 (Open Web Text)

Max Activating Token Index: 662

Text #6

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4516. Min Act: -0.1700

Data Index: 503828 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4444. Min Act: -0.1700

Data Index: 8741071 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4490. Min Act: -0.1700

Data Index: 3762907 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4354. Min Act: -0.1699

Data Index: 6823882 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4303. Min Act: -0.1700

Data Index: 4871186 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4240. Min Act: -0.1700

Data Index: 8117738 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4373. Min Act: -0.1699

Data Index: 7179689 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4304. Min Act: -0.1700

Data Index: 4135623 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4154. Min Act: -0.1697

Data Index: 1377349 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4188. Min Act: -0.1700

Data Index: 5790965 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4131. Min Act: -0.1694

Data Index: 5920752 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4045. Min Act: -0.1700

Data Index: 3794697 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4006. Min Act: -0.1697

Data Index: 4520267 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4045. Min Act: -0.1700

Data Index: 4118111 (Open Web Text)

Max Activating Token Index: 3