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

Dataset: Open Web Text

Neuron 1568 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: 1.3256. Min Range: -1.3256

Max Act: 1.3234. Min Act: -0.1698

Data Index: 5740019 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.3256. Min Act: -0.1687

Data Index: 3625960 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.3254. Min Act: -0.1676

Data Index: 6009280 (Open Web Text)

Max Activating Token Index: 779

Text #3

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.3158. Min Act: -0.1684

Data Index: 2496326 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.3043. Min Act: -0.1700

Data Index: 6444277 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.3043. Min Act: -0.1586

Data Index: 3032714 (Open Web Text)

Max Activating Token Index: 107

Text #6

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2889. Min Act: -0.1694

Data Index: 2343004 (Open Web Text)

Max Activating Token Index: 152

Text #7

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2926. Min Act: -0.1700

Data Index: 7808192 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2931. Min Act: -0.1699

Data Index: 3841326 (Open Web Text)

Max Activating Token Index: 226

Text #9

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2898. Min Act: -0.1698

Data Index: 7163267 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2772. Min Act: -0.1661

Data Index: 719000 (Open Web Text)

Max Activating Token Index: 614

Text #11

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2837. Min Act: -0.1700

Data Index: 4984328 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2793. Min Act: -0.1699

Data Index: 4759493 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2855. Min Act: -0.1700

Data Index: 7891042 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2722. Min Act: -0.1615

Data Index: 7740248 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2788. Min Act: -0.1692

Data Index: 5378539 (Open Web Text)

Max Activating Token Index: 534

Text #16

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2696. Min Act: -0.1692

Data Index: 737970 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2762. Min Act: -0.1685

Data Index: 2496325 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2777. Min Act: -0.1508

Data Index: 1095441 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2701. Min Act: -0.1693

Data Index: 2145278 (Open Web Text)

Max Activating Token Index: 648