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

Dataset: Open Web Text

Neuron 637 in Layer 4

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: 3.6675. Min Range: -3.6675

Max Act: 3.6675. Min Act: -0.1700

Data Index: 4138252 (Open Web Text)

Max Activating Token Index: 902

Text #1

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5459. Min Act: -0.1700

Data Index: 3659391 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5502. Min Act: -0.1700

Data Index: 1056028 (Open Web Text)

Max Activating Token Index: 622

Text #3

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5433. Min Act: -0.1700

Data Index: 6626905 (Open Web Text)

Max Activating Token Index: 697

Text #4

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5425. Min Act: -0.1700

Data Index: 811838 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5238. Min Act: -0.1700

Data Index: 8829162 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5355. Min Act: -0.1700

Data Index: 4419041 (Open Web Text)

Max Activating Token Index: 636

Text #7

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5614. Min Act: -0.1700

Data Index: 8418700 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5489. Min Act: -0.1700

Data Index: 7334464 (Open Web Text)

Max Activating Token Index: 736

Text #9

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5014. Min Act: -0.1700

Data Index: 3221525 (Open Web Text)

Max Activating Token Index: 583

Text #10

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5275. Min Act: -0.1700

Data Index: 3229721 (Open Web Text)

Max Activating Token Index: 158

Text #11

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5042. Min Act: -0.1700

Data Index: 7453877 (Open Web Text)

Max Activating Token Index: 294

Text #12

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.4682. Min Act: -0.1700

Data Index: 1095413 (Open Web Text)

Max Activating Token Index: 846

Text #13

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5081. Min Act: -0.1700

Data Index: 523257 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5133. Min Act: -0.1700

Data Index: 7214338 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.4958. Min Act: -0.1700

Data Index: 4585397 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.5048. Min Act: -0.1700

Data Index: 7823736 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.4383. Min Act: -0.1700

Data Index: 5602814 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.4456. Min Act: -0.1700

Data Index: 1935295 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 3.6675. Min Range: -3.6675

Max Act: 3.4430. Min Act: -0.1700

Data Index: 8443393 (Open Web Text)

Max Activating Token Index: 558