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

Dataset: Open Web Text

Neuron 2839 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: 4.0912. Min Range: -4.0912

Max Act: 4.0861. Min Act: -0.1700

Data Index: 1547352 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0838. Min Act: -0.1700

Data Index: 4671643 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0838. Min Act: -0.1700

Data Index: 1661318 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0912. Min Act: -0.1700

Data Index: 1064102 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0491. Min Act: -0.1700

Data Index: 5786306 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0530. Min Act: -0.1700

Data Index: 1290908 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0491. Min Act: -0.1700

Data Index: 3587838 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0183. Min Act: -0.1700

Data Index: 4013453 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0383. Min Act: -0.1700

Data Index: 5880489 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0219. Min Act: -0.1700

Data Index: 7633802 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0376. Min Act: -0.1700

Data Index: 5591857 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.0912. Min Range: -4.0912

Max Act: 4.0168. Min Act: -0.1700

Data Index: 134937 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9808. Min Act: -0.1700

Data Index: 5052859 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9931. Min Act: -0.1700

Data Index: 4920682 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9893. Min Act: -0.1700

Data Index: 3595489 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9946. Min Act: -0.1700

Data Index: 4903957 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9893. Min Act: -0.1700

Data Index: 4800946 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9839. Min Act: -0.1700

Data Index: 1374882 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9786. Min Act: -0.1700

Data Index: 3148830 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0912. Min Range: -4.0912

Max Act: 3.9793. Min Act: -0.1700

Data Index: 904185 (Open Web Text)

Max Activating Token Index: 4