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

Dataset: Open Web Text

Neuron 2817 in Layer 3

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: 4.1394. Min Range: -4.1394

Max Act: 4.1394. Min Act: -0.1700

Data Index: 3711196 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 4.1394. Min Range: -4.1394

Max Act: 4.1335. Min Act: -0.1700

Data Index: 8661730 (Open Web Text)

Max Activating Token Index: 216

Text #2

Max Range: 4.1394. Min Range: -4.1394

Max Act: 4.1224. Min Act: -0.1700

Data Index: 6281647 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 4.1394. Min Range: -4.1394

Max Act: 4.0956. Min Act: -0.1700

Data Index: 2254670 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 4.1394. Min Range: -4.1394

Max Act: 4.0371. Min Act: -0.1700

Data Index: 4617380 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.9508. Min Act: -0.1700

Data Index: 2886399 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.9341. Min Act: -0.1700

Data Index: 2171960 (Open Web Text)

Max Activating Token Index: 904

Text #7

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.9128. Min Act: -0.1700

Data Index: 8538730 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.9056. Min Act: -0.1700

Data Index: 6607591 (Open Web Text)

Max Activating Token Index: 925

Text #9

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.9117. Min Act: -0.1700

Data Index: 218391 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8548. Min Act: -0.1700

Data Index: 3721189 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8497. Min Act: -0.1700

Data Index: 39904 (Open Web Text)

Max Activating Token Index: 716

Text #12

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8314. Min Act: -0.1700

Data Index: 8427489 (Open Web Text)

Max Activating Token Index: 42

Text #13

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8222. Min Act: -0.1700

Data Index: 7855031 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8454. Min Act: -0.1700

Data Index: 4606679 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8290. Min Act: -0.1700

Data Index: 1612775 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8125. Min Act: -0.1700

Data Index: 5071607 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8026. Min Act: -0.1700

Data Index: 4883131 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.8462. Min Act: -0.1700

Data Index: 8661729 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 4.1394. Min Range: -4.1394

Max Act: 3.7810. Min Act: -0.1700

Data Index: 5880599 (Open Web Text)

Max Activating Token Index: 410