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

Dataset: Open Web Text

Neuron 781 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: 3.3394. Min Range: -3.3394

Max Act: 3.3394. Min Act: -0.1700

Data Index: 7303890 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.3195. Min Act: -0.1700

Data Index: 8634926 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.2896. Min Act: -0.1700

Data Index: 4994474 (Open Web Text)

Max Activating Token Index: 563

Text #3

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.2483. Min Act: -0.1700

Data Index: 2111696 (Open Web Text)

Max Activating Token Index: 936

Text #4

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1525. Min Act: -0.1700

Data Index: 2703076 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1619. Min Act: -0.1700

Data Index: 8019962 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1582. Min Act: -0.1700

Data Index: 2151981 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1374. Min Act: -0.1700

Data Index: 5388263 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1576. Min Act: -0.1700

Data Index: 1840719 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1443018 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.1194. Min Act: -0.1700

Data Index: 8634925 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0835. Min Act: -0.1700

Data Index: 2057511 (Open Web Text)

Max Activating Token Index: 593

Text #12

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0791. Min Act: -0.1700

Data Index: 5397732 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0908. Min Act: -0.1700

Data Index: 8039895 (Open Web Text)

Max Activating Token Index: 215

Text #14

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0921. Min Act: -0.1700

Data Index: 8616520 (Open Web Text)

Max Activating Token Index: 325

Text #15

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0991. Min Act: -0.1700

Data Index: 3546125 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0862. Min Act: -0.1700

Data Index: 6747791 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0890. Min Act: -0.1700

Data Index: 8783862 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0483. Min Act: -0.1700

Data Index: 7152076 (Open Web Text)

Max Activating Token Index: 244

Text #19

Max Range: 3.3394. Min Range: -3.3394

Max Act: 3.0536. Min Act: -0.1700

Data Index: 6278782 (Open Web Text)

Max Activating Token Index: 49