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

Dataset: Open Web Text

Neuron 1598 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: 3.2051. Min Range: -3.2051

Max Act: 3.2051. Min Act: -0.1700

Data Index: 2724429 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1751. Min Act: -0.1700

Data Index: 6199113 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1670. Min Act: -0.1700

Data Index: 5576733 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1617. Min Act: -0.1700

Data Index: 922930 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1473. Min Act: -0.1700

Data Index: 3512946 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1557. Min Act: -0.1700

Data Index: 2408259 (Open Web Text)

Max Activating Token Index: 824

Text #6

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1510. Min Act: -0.1700

Data Index: 1266046 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1422. Min Act: -0.1700

Data Index: 3342398 (Open Web Text)

Max Activating Token Index: 304

Text #8

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1511. Min Act: -0.1700

Data Index: 3367824 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1497. Min Act: -0.1700

Data Index: 3493013 (Open Web Text)

Max Activating Token Index: 1008

Text #10

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1181. Min Act: -0.1700

Data Index: 8820952 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1196. Min Act: -0.1700

Data Index: 6026940 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1167. Min Act: -0.1700

Data Index: 324460 (Open Web Text)

Max Activating Token Index: 752

Text #13

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1372. Min Act: -0.1700

Data Index: 3795957 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1405. Min Act: -0.1700

Data Index: 4771776 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.0977. Min Act: -0.1700

Data Index: 97338 (Open Web Text)

Max Activating Token Index: 378

Text #16

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1067. Min Act: -0.1700

Data Index: 1887033 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1101. Min Act: -0.1700

Data Index: 4750056 (Open Web Text)

Max Activating Token Index: 954

Text #18

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1162. Min Act: -0.1700

Data Index: 2995071 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 3.2051. Min Range: -3.2051

Max Act: 3.1124. Min Act: -0.1700

Data Index: 4878244 (Open Web Text)

Max Activating Token Index: 190