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

Dataset: Open Web Text

Neuron 2570 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: 3.8595. Min Range: -3.8595

Max Act: 3.8595. Min Act: -0.1700

Data Index: 7397490 (Open Web Text)

Max Activating Token Index: 921

Text #1

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.8165. Min Act: -0.1700

Data Index: 320916 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.7722. Min Act: -0.1700

Data Index: 6513615 (Open Web Text)

Max Activating Token Index: 272

Text #3

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.7369. Min Act: -0.1700

Data Index: 4178172 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.7236. Min Act: -0.1700

Data Index: 1401357 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1766121 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6878. Min Act: -0.1700

Data Index: 3426078 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6783. Min Act: -0.1700

Data Index: 6239746 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6904. Min Act: -0.1700

Data Index: 1560939 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6626. Min Act: -0.1700

Data Index: 7426201 (Open Web Text)

Max Activating Token Index: 664

Text #10

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6402. Min Act: -0.1700

Data Index: 1625098 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6519. Min Act: -0.1700

Data Index: 4767659 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6756. Min Act: -0.1700

Data Index: 6609315 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6472. Min Act: -0.1700

Data Index: 8474364 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6835. Min Act: -0.1700

Data Index: 3450917 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6619. Min Act: -0.1700

Data Index: 6660873 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6666. Min Act: -0.1700

Data Index: 3442966 (Open Web Text)

Max Activating Token Index: 202

Text #17

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6732. Min Act: -0.1700

Data Index: 597078 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6451. Min Act: -0.1700

Data Index: 2023424 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6452. Min Act: -0.1700

Data Index: 6912227 (Open Web Text)

Max Activating Token Index: 793