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

Dataset: Open Web Text

Neuron 1061 in Layer 5

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: 3.2773. Min Range: -3.2773

Max Act: 3.2773. Min Act: -0.1700

Data Index: 3801806 (Open Web Text)

Max Activating Token Index: 131

Text #1

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.2171. Min Act: -0.1700

Data Index: 6414264 (Open Web Text)

Max Activating Token Index: 787

Text #2

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.1044. Min Act: -0.1700

Data Index: 5497881 (Open Web Text)

Max Activating Token Index: 289

Text #3

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0938. Min Act: -0.1700

Data Index: 4681289 (Open Web Text)

Max Activating Token Index: 155

Text #4

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0219. Min Act: -0.1700

Data Index: 8586673 (Open Web Text)

Max Activating Token Index: 736

Text #5

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0360. Min Act: -0.1700

Data Index: 6436354 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0234. Min Act: -0.1700

Data Index: 2654145 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0032. Min Act: -0.1700

Data Index: 7446765 (Open Web Text)

Max Activating Token Index: 140

Text #8

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0051. Min Act: -0.1700

Data Index: 4356757 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0041. Min Act: -0.1700

Data Index: 7439386 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0200. Min Act: -0.1700

Data Index: 5158088 (Open Web Text)

Max Activating Token Index: 795

Text #11

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0063. Min Act: -0.1700

Data Index: 6362715 (Open Web Text)

Max Activating Token Index: 117

Text #12

Max Range: 3.2773. Min Range: -3.2773

Max Act: 3.0065. Min Act: -0.1700

Data Index: 6314293 (Open Web Text)

Max Activating Token Index: 141

Text #13

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9845. Min Act: -0.1700

Data Index: 7190314 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9957. Min Act: -0.1700

Data Index: 3261373 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9893. Min Act: -0.1700

Data Index: 7662268 (Open Web Text)

Max Activating Token Index: 551

Text #16

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9847. Min Act: -0.1700

Data Index: 7210013 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9638. Min Act: -0.1700

Data Index: 5098855 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9722. Min Act: -0.1700

Data Index: 4162473 (Open Web Text)

Max Activating Token Index: 218

Text #19

Max Range: 3.2773. Min Range: -3.2773

Max Act: 2.9711. Min Act: -0.1700

Data Index: 5545541 (Open Web Text)

Max Activating Token Index: 959