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

Dataset: Open Web Text

Neuron 1252 in Layer 3

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: 3.4148. Min Range: -3.4148

Max Act: 3.4007. Min Act: -0.1700

Data Index: 8536418 (Open Web Text)

Max Activating Token Index: 335

Text #1

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1185242 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.4148. Min Act: -0.1700

Data Index: 6926158 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3887. Min Act: -0.1700

Data Index: 8722920 (Open Web Text)

Max Activating Token Index: 236

Text #4

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3809. Min Act: -0.1700

Data Index: 5359424 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3696. Min Act: -0.1700

Data Index: 4141027 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3783. Min Act: -0.1700

Data Index: 5265621 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3626. Min Act: -0.1700

Data Index: 2313418 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1140331 (Open Web Text)

Max Activating Token Index: 799

Text #9

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3582. Min Act: -0.1700

Data Index: 5226650 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3324. Min Act: -0.1700

Data Index: 6310931 (Open Web Text)

Max Activating Token Index: 821

Text #11

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3249. Min Act: -0.1700

Data Index: 3292091 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3577. Min Act: -0.1700

Data Index: 7300073 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1894982 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3250. Min Act: -0.1700

Data Index: 2005734 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3311. Min Act: -0.1700

Data Index: 3261084 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3105. Min Act: -0.1700

Data Index: 7685987 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3174. Min Act: -0.1700

Data Index: 4047857 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3151. Min Act: -0.1700

Data Index: 3267832 (Open Web Text)

Max Activating Token Index: 44

Text #19

Max Range: 3.4148. Min Range: -3.4148

Max Act: 3.3215. Min Act: -0.1700

Data Index: 5909915 (Open Web Text)

Max Activating Token Index: 643