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

Dataset: Open Web Text

Neuron 1611 in Layer 5

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: 4.8531. Min Range: -4.8531

Max Act: 4.8071. Min Act: -0.1698

Data Index: 6391237 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.8500. Min Act: -0.1700

Data Index: 3577924 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.8531. Min Act: -0.1526

Data Index: 6351681 (Open Web Text)

Max Activating Token Index: 760

Text #3

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.7886. Min Act: -0.1699

Data Index: 3651933 (Open Web Text)

Max Activating Token Index: 797

Text #4

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.7198. Min Act: -0.1700

Data Index: 6351677 (Open Web Text)

Max Activating Token Index: 343

Text #5

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.7313. Min Act: -0.1690

Data Index: 4619941 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.6525. Min Act: -0.1699

Data Index: 3436740 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.6559. Min Act: -0.1700

Data Index: 7364906 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.6291. Min Act: -0.1562

Data Index: 1451330 (Open Web Text)

Max Activating Token Index: 867

Text #9

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5740. Min Act: -0.1700

Data Index: 2936882 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5510. Min Act: -0.1700

Data Index: 1791301 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5430. Min Act: -0.1700

Data Index: 3017140 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5292. Min Act: -0.1700

Data Index: 5089341 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5733. Min Act: -0.1699

Data Index: 6061088 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5837. Min Act: -0.1672

Data Index: 1465655 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5199. Min Act: -0.1700

Data Index: 1200863 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5899. Min Act: -0.1700

Data Index: 3711043 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5139. Min Act: -0.1700

Data Index: 6143707 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5001. Min Act: -0.1699

Data Index: 6061091 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5465. Min Act: -0.1698

Data Index: 218120 (Open Web Text)

Max Activating Token Index: 44