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

Dataset: Open Web Text

Neuron 846 in Layer 0

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: 1.9727. Min Range: -1.9727

Max Act: 1.9727. Min Act: -0.1700

Data Index: 4551654 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9313. Min Act: -0.1700

Data Index: 5600240 (Open Web Text)

Max Activating Token Index: 424

Text #2

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9257. Min Act: -0.1700

Data Index: 6303965 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9036. Min Act: -0.1700

Data Index: 4937455 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8963. Min Act: -0.1700

Data Index: 7504827 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9078. Min Act: -0.1700

Data Index: 4939310 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9122. Min Act: -0.1700

Data Index: 4798380 (Open Web Text)

Max Activating Token Index: 1007

Text #7

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8979. Min Act: -0.1700

Data Index: 181323 (Open Web Text)

Max Activating Token Index: 841

Text #8

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8919. Min Act: -0.1700

Data Index: 2270087 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8874. Min Act: -0.1698

Data Index: 2012562 (Open Web Text)

Max Activating Token Index: 266

Text #10

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8853. Min Act: -0.1700

Data Index: 1142170 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8890. Min Act: -0.1700

Data Index: 7463712 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8911. Min Act: -0.1694

Data Index: 500571 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8861. Min Act: -0.1700

Data Index: 6987759 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8832. Min Act: -0.1700

Data Index: 351428 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8724. Min Act: -0.1700

Data Index: 6025615 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8767. Min Act: -0.1699

Data Index: 8155410 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8720. Min Act: -0.1700

Data Index: 7161166 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8743. Min Act: -0.1700

Data Index: 2192814 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8604. Min Act: -0.1695

Data Index: 1774030 (Open Web Text)

Max Activating Token Index: 917