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

Dataset: Open Web Text

Neuron 1666 in Layer 6

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: 3.1449. Min Range: -3.1449

Max Act: 3.1449. Min Act: -0.1700

Data Index: 3856109 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0901. Min Act: -0.1700

Data Index: 7193043 (Open Web Text)

Max Activating Token Index: 414

Text #2

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0887. Min Act: -0.1700

Data Index: 5229718 (Open Web Text)

Max Activating Token Index: 754

Text #3

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0891. Min Act: -0.1700

Data Index: 7141616 (Open Web Text)

Max Activating Token Index: 899

Text #4

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0897. Min Act: -0.1700

Data Index: 7551731 (Open Web Text)

Max Activating Token Index: 671

Text #5

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0027. Min Act: -0.1700

Data Index: 713110 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0430. Min Act: -0.1700

Data Index: 7013288 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0139. Min Act: -0.1700

Data Index: 5381711 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0362. Min Act: -0.1700

Data Index: 4521010 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9866. Min Act: -0.1700

Data Index: 5933272 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9990. Min Act: -0.1700

Data Index: 1256458 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9956. Min Act: -0.1700

Data Index: 5419696 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9969. Min Act: -0.1700

Data Index: 2411970 (Open Web Text)

Max Activating Token Index: 751

Text #13

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0086. Min Act: -0.1700

Data Index: 4890416 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9774. Min Act: -0.1700

Data Index: 1483008 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9433. Min Act: -0.1700

Data Index: 4236466 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9433. Min Act: -0.1700

Data Index: 266852 (Open Web Text)

Max Activating Token Index: 201

Text #17

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9509. Min Act: -0.1700

Data Index: 6550959 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9440. Min Act: -0.1700

Data Index: 3557277 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9285. Min Act: -0.1700

Data Index: 1198800 (Open Web Text)

Max Activating Token Index: 164