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

Dataset: Open Web Text

Neuron 2889 in Layer 3

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: 4.1004. Min Range: -4.1004

Max Act: 4.1004. Min Act: -0.1700

Data Index: 3694175 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.9518. Min Act: -0.1700

Data Index: 2028778 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.9097. Min Act: -0.1700

Data Index: 821672 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7793. Min Act: -0.1700

Data Index: 612281 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1627598 (Open Web Text)

Max Activating Token Index: 730

Text #5

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7679. Min Act: -0.1700

Data Index: 1880027 (Open Web Text)

Max Activating Token Index: 203

Text #6

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7118. Min Act: -0.1700

Data Index: 2021406 (Open Web Text)

Max Activating Token Index: 168

Text #7

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7093. Min Act: -0.1700

Data Index: 7510018 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7426. Min Act: -0.1700

Data Index: 8260241 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7190. Min Act: -0.1700

Data Index: 7418550 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.7128. Min Act: -0.1700

Data Index: 7272266 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6842. Min Act: -0.1700

Data Index: 7028307 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6674. Min Act: -0.1700

Data Index: 8519201 (Open Web Text)

Max Activating Token Index: 444

Text #13

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6881. Min Act: -0.1700

Data Index: 5726715 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6757. Min Act: -0.1700

Data Index: 2746384 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6571. Min Act: -0.1700

Data Index: 5036015 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6459. Min Act: -0.1700

Data Index: 1283359 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6557. Min Act: -0.1700

Data Index: 543599 (Open Web Text)

Max Activating Token Index: 860

Text #18

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6009. Min Act: -0.1700

Data Index: 4280827 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 4.1004. Min Range: -4.1004

Max Act: 3.6288. Min Act: -0.1700

Data Index: 566341 (Open Web Text)

Max Activating Token Index: 758