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

Dataset: Open Web Text

Neuron 915 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: 2.1106. Min Range: -2.1106

Max Act: 2.1106. Min Act: -0.1700

Data Index: 2732522 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0902. Min Act: -0.1700

Data Index: 3218314 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.1029. Min Act: -0.1700

Data Index: 4772774 (Open Web Text)

Max Activating Token Index: 701

Text #3

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.1014. Min Act: -0.1700

Data Index: 3491568 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.1026. Min Act: -0.1700

Data Index: 3739167 (Open Web Text)

Max Activating Token Index: 219

Text #5

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.1054. Min Act: -0.1700

Data Index: 1705368 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0978. Min Act: -0.1700

Data Index: 7222697 (Open Web Text)

Max Activating Token Index: 702

Text #7

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0887. Min Act: -0.1700

Data Index: 7461434 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0863. Min Act: -0.1700

Data Index: 3164723 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0957. Min Act: -0.1700

Data Index: 725873 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0841. Min Act: -0.1700

Data Index: 4847407 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0763. Min Act: -0.1700

Data Index: 4642992 (Open Web Text)

Max Activating Token Index: 750

Text #12

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0625. Min Act: -0.1699

Data Index: 6572044 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0673. Min Act: -0.1700

Data Index: 4528756 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0761. Min Act: -0.1700

Data Index: 6749964 (Open Web Text)

Max Activating Token Index: 257

Text #15

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0634. Min Act: -0.1700

Data Index: 6025815 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0659. Min Act: -0.1700

Data Index: 4207123 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0695. Min Act: -0.1700

Data Index: 4955110 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0668. Min Act: -0.1700

Data Index: 183909 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 2.1106. Min Range: -2.1106

Max Act: 2.0596. Min Act: -0.1700

Data Index: 3161773 (Open Web Text)

Max Activating Token Index: 288