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

Dataset: Open Web Text

Neuron 2425 in Layer 6

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: 3.0036. Min Range: -3.0036

Max Act: 3.0036. Min Act: -0.1700

Data Index: 7255795 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 3.0036. Min Range: -3.0036

Max Act: 3.0032. Min Act: -0.1700

Data Index: 2967110 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9839. Min Act: -0.1700

Data Index: 6274911 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9615. Min Act: -0.1700

Data Index: 4053453 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9545. Min Act: -0.1700

Data Index: 800544 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9222. Min Act: -0.1700

Data Index: 712901 (Open Web Text)

Max Activating Token Index: 171

Text #6

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9265. Min Act: -0.1700

Data Index: 8148381 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8970. Min Act: -0.1700

Data Index: 4942884 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9034. Min Act: -0.1700

Data Index: 2951439 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.9057. Min Act: -0.1700

Data Index: 5226744 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8627. Min Act: -0.1700

Data Index: 3984417 (Open Web Text)

Max Activating Token Index: 330

Text #11

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8775. Min Act: -0.1700

Data Index: 4680814 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8543. Min Act: -0.1700

Data Index: 3628862 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8834. Min Act: -0.1700

Data Index: 1184657 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8809. Min Act: -0.1700

Data Index: 2162672 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8325. Min Act: -0.1700

Data Index: 1167499 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1742792 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8424. Min Act: -0.1700

Data Index: 6814342 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8215. Min Act: -0.1700

Data Index: 797460 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 3.0036. Min Range: -3.0036

Max Act: 2.8476. Min Act: -0.1700

Data Index: 8025428 (Open Web Text)

Max Activating Token Index: 72