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

Dataset: Open Web Text

Neuron 1935 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: 2.0759. Min Range: -2.0759

Max Act: 2.0759. Min Act: -0.1693

Data Index: 7595689 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.0759. Min Range: -2.0759

Max Act: 2.0307. Min Act: -0.1693

Data Index: 4554026 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.0759. Min Range: -2.0759

Max Act: 2.0064. Min Act: -0.1700

Data Index: 5622553 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.0759. Min Range: -2.0759

Max Act: 2.0139. Min Act: -0.1696

Data Index: 2162926 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.0759. Min Range: -2.0759

Max Act: 2.0068. Min Act: -0.1700

Data Index: 3936776 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.0759. Min Range: -2.0759

Max Act: 2.0084. Min Act: -0.1693

Data Index: 277206 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9981. Min Act: -0.1693

Data Index: 7179283 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9961. Min Act: -0.1700

Data Index: 8661258 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.0759. Min Range: -2.0759

Max Act: 2.0048. Min Act: -0.1696

Data Index: 862895 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9832. Min Act: -0.1700

Data Index: 7083205 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9850. Min Act: -0.1700

Data Index: 958758 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9810. Min Act: -0.1700

Data Index: 3961723 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9728. Min Act: -0.1700

Data Index: 881070 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9810. Min Act: -0.1700

Data Index: 1578608 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9832. Min Act: -0.1700

Data Index: 6305098 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9810. Min Act: -0.1700

Data Index: 569492 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9810. Min Act: -0.1693

Data Index: 1400528 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9781. Min Act: -0.1700

Data Index: 501679 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9832. Min Act: -0.1700

Data Index: 3325953 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 2.0759. Min Range: -2.0759

Max Act: 1.9706. Min Act: -0.1698

Data Index: 4530472 (Open Web Text)

Max Activating Token Index: 2