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

Dataset: Open Web Text

Neuron 1003 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: 4.6512. Min Range: -4.6512

Max Act: 4.6512. Min Act: -0.1700

Data Index: 658798 (Open Web Text)

Max Activating Token Index: 744

Text #1

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5717. Min Act: -0.1700

Data Index: 7641079 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5229. Min Act: -0.1700

Data Index: 820195 (Open Web Text)

Max Activating Token Index: 468

Text #3

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.4891. Min Act: -0.1700

Data Index: 8063682 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5208. Min Act: -0.1700

Data Index: 2871098 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5013. Min Act: -0.1700

Data Index: 6939258 (Open Web Text)

Max Activating Token Index: 157

Text #6

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3972. Min Act: -0.1700

Data Index: 6401985 (Open Web Text)

Max Activating Token Index: 714

Text #7

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.4015. Min Act: -0.1700

Data Index: 6413198 (Open Web Text)

Max Activating Token Index: 888

Text #8

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3768. Min Act: -0.1700

Data Index: 5271252 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3867. Min Act: -0.1700

Data Index: 3831870 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3721. Min Act: -0.1700

Data Index: 897054 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3400. Min Act: -0.1700

Data Index: 5941759 (Open Web Text)

Max Activating Token Index: 430

Text #12

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3366. Min Act: -0.1700

Data Index: 5509821 (Open Web Text)

Max Activating Token Index: 956

Text #13

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3127. Min Act: -0.1700

Data Index: 1471542 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.4119. Min Act: -0.1700

Data Index: 2692857 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3086. Min Act: -0.1700

Data Index: 5058279 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3283. Min Act: -0.1700

Data Index: 6421713 (Open Web Text)

Max Activating Token Index: 531

Text #17

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3347. Min Act: -0.1700

Data Index: 209132 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.2741. Min Act: -0.1700

Data Index: 5723566 (Open Web Text)

Max Activating Token Index: 550

Text #19

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.3346. Min Act: -0.1700

Data Index: 4966151 (Open Web Text)

Max Activating Token Index: 603