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

Dataset: Open Web Text

Neuron 1313 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: 3.4822. Min Range: -3.4822

Max Act: 3.4822. Min Act: -0.1700

Data Index: 6270563 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.4748. Min Act: -0.1700

Data Index: 5608162 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.4598. Min Act: -0.1700

Data Index: 8275445 (Open Web Text)

Max Activating Token Index: 754

Text #3

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.4210. Min Act: -0.1700

Data Index: 5705381 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3593. Min Act: -0.1700

Data Index: 4499608 (Open Web Text)

Max Activating Token Index: 903

Text #5

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3628. Min Act: -0.1700

Data Index: 4684700 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3413. Min Act: -0.1700

Data Index: 8723278 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3701. Min Act: -0.1700

Data Index: 4804422 (Open Web Text)

Max Activating Token Index: 239

Text #8

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3394. Min Act: -0.1700

Data Index: 5410016 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3422. Min Act: -0.1700

Data Index: 4803537 (Open Web Text)

Max Activating Token Index: 292

Text #10

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3133. Min Act: -0.1700

Data Index: 7346858 (Open Web Text)

Max Activating Token Index: 839

Text #11

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3391. Min Act: -0.1700

Data Index: 6017174 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.2862. Min Act: -0.1700

Data Index: 6802701 (Open Web Text)

Max Activating Token Index: 786

Text #13

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3070. Min Act: -0.1700

Data Index: 347726 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3429. Min Act: -0.1700

Data Index: 8334974 (Open Web Text)

Max Activating Token Index: 660

Text #15

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3297. Min Act: -0.1700

Data Index: 1155945 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3172. Min Act: -0.1700

Data Index: 1197108 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3023. Min Act: -0.1700

Data Index: 3135002 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3013. Min Act: -0.1700

Data Index: 2573467 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3058. Min Act: -0.1700

Data Index: 5753340 (Open Web Text)

Max Activating Token Index: 404