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

Dataset: Open Web Text

Neuron 678 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: 5.7854. Min Range: -5.7854

Max Act: 5.7854. Min Act: -0.1700

Data Index: 612250 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7643. Min Act: -0.1700

Data Index: 2905322 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7106. Min Act: -0.1700

Data Index: 1086640 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7232. Min Act: -0.1700

Data Index: 1611418 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7336. Min Act: -0.1700

Data Index: 1720164 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7259. Min Act: -0.1700

Data Index: 4500992 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7232. Min Act: -0.1700

Data Index: 2412604 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7285. Min Act: -0.1700

Data Index: 6122179 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.7025. Min Act: -0.1700

Data Index: 8559954 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6944. Min Act: -0.1699

Data Index: 667050 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6953. Min Act: -0.1700

Data Index: 1592666 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6570. Min Act: -0.1700

Data Index: 6634262 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6690. Min Act: -0.1700

Data Index: 830004 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6609. Min Act: -0.1700

Data Index: 3591286 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6618. Min Act: -0.1700

Data Index: 8798614 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6638. Min Act: -0.1700

Data Index: 6029947 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6903. Min Act: -0.1700

Data Index: 4826954 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6636. Min Act: -0.1700

Data Index: 1294768 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6325. Min Act: -0.1700

Data Index: 671043 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.7854. Min Range: -5.7854

Max Act: 5.6346. Min Act: -0.1700

Data Index: 4845250 (Open Web Text)

Max Activating Token Index: 3