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

Dataset: Open Web Text

Neuron 1369 in Layer 4

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: 3.0508. Min Range: -3.0508

Max Act: 3.0508. Min Act: -0.1700

Data Index: 257360 (Open Web Text)

Max Activating Token Index: 402

Text #1

Max Range: 3.0508. Min Range: -3.0508

Max Act: 3.0137. Min Act: -0.1700

Data Index: 8471736 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 3.0508. Min Range: -3.0508

Max Act: 3.0317. Min Act: -0.1700

Data Index: 8497290 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9970. Min Act: -0.1700

Data Index: 3535502 (Open Web Text)

Max Activating Token Index: 591

Text #4

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9848. Min Act: -0.1700

Data Index: 7042953 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9991. Min Act: -0.1700

Data Index: 5251624 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9725. Min Act: -0.1700

Data Index: 4874300 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9282. Min Act: -0.1700

Data Index: 6740935 (Open Web Text)

Max Activating Token Index: 863

Text #8

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9534. Min Act: -0.1700

Data Index: 8184226 (Open Web Text)

Max Activating Token Index: 766

Text #9

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9104. Min Act: -0.1700

Data Index: 8531886 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8955. Min Act: -0.1700

Data Index: 4438480 (Open Web Text)

Max Activating Token Index: 397

Text #11

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9082. Min Act: -0.1700

Data Index: 2700078 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9008. Min Act: -0.1700

Data Index: 1777264 (Open Web Text)

Max Activating Token Index: 630

Text #13

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8837. Min Act: -0.1700

Data Index: 3869022 (Open Web Text)

Max Activating Token Index: 137

Text #14

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8789. Min Act: -0.1700

Data Index: 7958093 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8766. Min Act: -0.1700

Data Index: 7432890 (Open Web Text)

Max Activating Token Index: 665

Text #16

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8548. Min Act: -0.1700

Data Index: 2274178 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8497. Min Act: -0.1700

Data Index: 2277585 (Open Web Text)

Max Activating Token Index: 777

Text #18

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8453. Min Act: -0.1700

Data Index: 4183290 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8644. Min Act: -0.1700

Data Index: 7091387 (Open Web Text)

Max Activating Token Index: 603