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

Dataset: Open Web Text

Neuron 2211 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: 4.6230. Min Range: -4.6230

Max Act: 4.6230. Min Act: -0.1700

Data Index: 544628 (Open Web Text)

Max Activating Token Index: 170

Text #1

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5555. Min Act: -0.1700

Data Index: 2072281 (Open Web Text)

Max Activating Token Index: 375

Text #2

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5511. Min Act: -0.1700

Data Index: 2727350 (Open Web Text)

Max Activating Token Index: 549

Text #3

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5247. Min Act: -0.1700

Data Index: 4971366 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4924. Min Act: -0.1700

Data Index: 1170617 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5018. Min Act: -0.1700

Data Index: 316112 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5106. Min Act: -0.1700

Data Index: 7458230 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4871. Min Act: -0.1700

Data Index: 7453415 (Open Web Text)

Max Activating Token Index: 917

Text #8

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5213. Min Act: -0.1700

Data Index: 1394339 (Open Web Text)

Max Activating Token Index: 653

Text #9

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4852. Min Act: -0.1700

Data Index: 4384472 (Open Web Text)

Max Activating Token Index: 182

Text #10

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5003. Min Act: -0.1700

Data Index: 2293886 (Open Web Text)

Max Activating Token Index: 661

Text #11

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5217. Min Act: -0.1700

Data Index: 1374190 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5120. Min Act: -0.1700

Data Index: 1664520 (Open Web Text)

Max Activating Token Index: 653

Text #13

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.5005. Min Act: -0.1700

Data Index: 1260314 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4900. Min Act: -0.1700

Data Index: 4246232 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4900. Min Act: -0.1700

Data Index: 3778267 (Open Web Text)

Max Activating Token Index: 922

Text #16

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4831. Min Act: -0.1700

Data Index: 5687475 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4844. Min Act: -0.1700

Data Index: 1926598 (Open Web Text)

Max Activating Token Index: 260

Text #18

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4736. Min Act: -0.1700

Data Index: 1471442 (Open Web Text)

Max Activating Token Index: 909

Text #19

Max Range: 4.6230. Min Range: -4.6230

Max Act: 4.4401. Min Act: -0.1700

Data Index: 1068752 (Open Web Text)

Max Activating Token Index: 745