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

Dataset: Open Web Text

Neuron 1478 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: 4.2702. Min Range: -4.2702

Max Act: 4.2702. Min Act: -0.1700

Data Index: 5979866 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.2335. Min Act: -0.1700

Data Index: 459729 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.2335. Min Act: -0.1700

Data Index: 4232736 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.2212. Min Act: -0.1700

Data Index: 6715207 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.2383. Min Act: -0.1700

Data Index: 6334704 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1825. Min Act: -0.1700

Data Index: 622290 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1792. Min Act: -0.1700

Data Index: 746687 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1792. Min Act: -0.1700

Data Index: 153004 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1792. Min Act: -0.1700

Data Index: 1187479 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1464. Min Act: -0.1700

Data Index: 7723055 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1499. Min Act: -0.1700

Data Index: 4961743 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1031. Min Act: -0.1700

Data Index: 1902607 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1095. Min Act: -0.1700

Data Index: 2783817 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1158. Min Act: -0.1700

Data Index: 2121148 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0636. Min Act: -0.1700

Data Index: 3514258 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0616. Min Act: -0.1700

Data Index: 1457495 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0636. Min Act: -0.1700

Data Index: 2859159 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0636. Min Act: -0.1700

Data Index: 6115099 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0636. Min Act: -0.1700

Data Index: 1982643 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0818. Min Act: -0.1700

Data Index: 6796563 (Open Web Text)

Max Activating Token Index: 3