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

Dataset: Open Web Text

Neuron 614 in Layer 2

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: 2.6837. Min Range: -2.6837

Max Act: 2.6669. Min Act: -0.1700

Data Index: 2084085 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6837. Min Act: -0.1700

Data Index: 1466150 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6602. Min Act: -0.1700

Data Index: 5318629 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6445. Min Act: -0.1700

Data Index: 7373296 (Open Web Text)

Max Activating Token Index: 799

Text #4

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6209. Min Act: -0.1700

Data Index: 2084084 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6014. Min Act: -0.1700

Data Index: 8618865 (Open Web Text)

Max Activating Token Index: 159

Text #6

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5992. Min Act: -0.1700

Data Index: 1754056 (Open Web Text)

Max Activating Token Index: 504

Text #7

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6209. Min Act: -0.1700

Data Index: 1605154 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6332. Min Act: -0.1700

Data Index: 4398806 (Open Web Text)

Max Activating Token Index: 901

Text #9

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6077. Min Act: -0.1700

Data Index: 2265492 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5961. Min Act: -0.1700

Data Index: 1516479 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6132. Min Act: -0.1700

Data Index: 6925503 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5715. Min Act: -0.1700

Data Index: 1559200 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5989. Min Act: -0.1700

Data Index: 7926500 (Open Web Text)

Max Activating Token Index: 136

Text #14

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5957. Min Act: -0.1700

Data Index: 6131842 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5833. Min Act: -0.1700

Data Index: 4880596 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5659. Min Act: -0.1700

Data Index: 1824979 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.6120. Min Act: -0.1700

Data Index: 2278748 (Open Web Text)

Max Activating Token Index: 731

Text #18

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5751. Min Act: -0.1700

Data Index: 190571 (Open Web Text)

Max Activating Token Index: 486

Text #19

Max Range: 2.6837. Min Range: -2.6837

Max Act: 2.5751. Min Act: -0.1700

Data Index: 1401665 (Open Web Text)

Max Activating Token Index: 872