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

Dataset: Open Web Text

Neuron 1657 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: 4.2208. Min Range: -4.2208

Max Act: 4.2208. Min Act: -0.1700

Data Index: 675883 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.1451. Min Act: -0.1700

Data Index: 1652489 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0902. Min Act: -0.1700

Data Index: 7040509 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0959. Min Act: -0.1700

Data Index: 1841638 (Open Web Text)

Max Activating Token Index: 786

Text #4

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0828. Min Act: -0.1700

Data Index: 4267421 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.1189. Min Act: -0.1700

Data Index: 6059592 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0822. Min Act: -0.1700

Data Index: 8415756 (Open Web Text)

Max Activating Token Index: 156

Text #7

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0922. Min Act: -0.1700

Data Index: 2231564 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0581. Min Act: -0.1700

Data Index: 4835638 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0617. Min Act: -0.1700

Data Index: 6494316 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0631. Min Act: -0.1700

Data Index: 6260600 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0680. Min Act: -0.1700

Data Index: 6117815 (Open Web Text)

Max Activating Token Index: 1019

Text #12

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0578. Min Act: -0.1700

Data Index: 5252313 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0488. Min Act: -0.1700

Data Index: 4666946 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0575. Min Act: -0.1700

Data Index: 4142023 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0595. Min Act: -0.1700

Data Index: 939178 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0678. Min Act: -0.1700

Data Index: 1897454 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0473. Min Act: -0.1700

Data Index: 3814648 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0818. Min Act: -0.1700

Data Index: 3486549 (Open Web Text)

Max Activating Token Index: 272

Text #19

Max Range: 4.2208. Min Range: -4.2208

Max Act: 4.0556. Min Act: -0.1700

Data Index: 2787180 (Open Web Text)

Max Activating Token Index: 523