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

Dataset: Open Web Text

Neuron 390 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: 3.9534. Min Range: -3.9534

Max Act: 3.9534. Min Act: -0.1700

Data Index: 2475596 (Open Web Text)

Max Activating Token Index: 463

Text #1

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.9311. Min Act: -0.1700

Data Index: 5103732 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.9203. Min Act: -0.1700

Data Index: 5676257 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8971. Min Act: -0.1700

Data Index: 7958466 (Open Web Text)

Max Activating Token Index: 169

Text #4

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8987. Min Act: -0.1700

Data Index: 6081736 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.9226. Min Act: -0.1700

Data Index: 5935872 (Open Web Text)

Max Activating Token Index: 68

Text #6

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8944. Min Act: -0.1700

Data Index: 5796891 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.9087. Min Act: -0.1700

Data Index: 5788102 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8934. Min Act: -0.1700

Data Index: 172635 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8741. Min Act: -0.1700

Data Index: 8087263 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8871. Min Act: -0.1700

Data Index: 6714861 (Open Web Text)

Max Activating Token Index: 455

Text #11

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8429. Min Act: -0.1700

Data Index: 8723129 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8429. Min Act: -0.1700

Data Index: 8361256 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8269. Min Act: -0.1700

Data Index: 5215264 (Open Web Text)

Max Activating Token Index: 205

Text #14

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8510. Min Act: -0.1700

Data Index: 6812447 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8185. Min Act: -0.1700

Data Index: 1999676 (Open Web Text)

Max Activating Token Index: 794

Text #16

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8305. Min Act: -0.1700

Data Index: 2092044 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8284. Min Act: -0.1700

Data Index: 3739060 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7947. Min Act: -0.1700

Data Index: 6781282 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8105. Min Act: -0.1700

Data Index: 4267483 (Open Web Text)

Max Activating Token Index: 614