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

Dataset: Open Web Text

Neuron 1157 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: 1.9927. Min Range: -1.9927

Max Act: 1.9779. Min Act: -0.1700

Data Index: 286857 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9927. Min Act: -0.1700

Data Index: 2192357 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9720. Min Act: -0.1700

Data Index: 7943862 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9762. Min Act: -0.1698

Data Index: 4323237 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9770. Min Act: -0.1700

Data Index: 5207100 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9883. Min Act: -0.1700

Data Index: 7458897 (Open Web Text)

Max Activating Token Index: 240

Text #6

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9606. Min Act: -0.1700

Data Index: 4314144 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9593. Min Act: -0.1700

Data Index: 8610111 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9643. Min Act: -0.1699

Data Index: 4811568 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9671. Min Act: -0.1700

Data Index: 6741685 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9796. Min Act: -0.1700

Data Index: 7104056 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9596. Min Act: -0.1700

Data Index: 4813574 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9532. Min Act: -0.1700

Data Index: 5261252 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9576. Min Act: -0.1700

Data Index: 5250914 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9578. Min Act: -0.1693

Data Index: 8015815 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9478. Min Act: -0.1700

Data Index: 2233946 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9581. Min Act: -0.1698

Data Index: 5956119 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9577. Min Act: -0.1700

Data Index: 5876279 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9604. Min Act: -0.1700

Data Index: 2118881 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9426. Min Act: -0.1699

Data Index: 3088979 (Open Web Text)

Max Activating Token Index: 647