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

Dataset: Open Web Text

Neuron 2932 in Layer 1

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: 3.8740. Min Range: -3.8740

Max Act: 3.8740. Min Act: -0.1700

Data Index: 2240978 (Open Web Text)

Max Activating Token Index: 524

Text #1

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8288. Min Act: -0.1700

Data Index: 3207651 (Open Web Text)

Max Activating Token Index: 780

Text #2

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8094. Min Act: -0.1700

Data Index: 669668 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8402. Min Act: -0.1691

Data Index: 8484731 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8390. Min Act: -0.1698

Data Index: 2263505 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8214. Min Act: -0.1700

Data Index: 7552631 (Open Web Text)

Max Activating Token Index: 147

Text #6

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8281. Min Act: -0.1696

Data Index: 634977 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8308. Min Act: -0.1700

Data Index: 581485 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7859. Min Act: -0.1700

Data Index: 1049857 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7429. Min Act: -0.1700

Data Index: 3547424 (Open Web Text)

Max Activating Token Index: 254

Text #10

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7016. Min Act: -0.1700

Data Index: 6434601 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6971. Min Act: -0.1700

Data Index: 3252332 (Open Web Text)

Max Activating Token Index: 374

Text #12

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7036. Min Act: -0.1700

Data Index: 6764036 (Open Web Text)

Max Activating Token Index: 573

Text #13

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7136. Min Act: -0.1700

Data Index: 136240 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7000. Min Act: -0.1700

Data Index: 4423611 (Open Web Text)

Max Activating Token Index: 767

Text #15

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7202. Min Act: -0.1699

Data Index: 4150256 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6826. Min Act: -0.1700

Data Index: 6269481 (Open Web Text)

Max Activating Token Index: 952

Text #17

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6905. Min Act: -0.1700

Data Index: 7552630 (Open Web Text)

Max Activating Token Index: 857

Text #18

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6887. Min Act: -0.1700

Data Index: 6198180 (Open Web Text)

Max Activating Token Index: 539

Text #19

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6915. Min Act: -0.1700

Data Index: 7613984 (Open Web Text)

Max Activating Token Index: 509