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

Dataset: Open Web Text

Neuron 1210 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: 4.9696. Min Range: -4.9696

Max Act: 4.9696. Min Act: -0.1700

Data Index: 7107001 (Open Web Text)

Max Activating Token Index: 402

Text #1

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.8954. Min Act: -0.1700

Data Index: 3997691 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.8726. Min Act: -0.1700

Data Index: 6834318 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7941. Min Act: -0.1700

Data Index: 2422181 (Open Web Text)

Max Activating Token Index: 1000

Text #4

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7373. Min Act: -0.1700

Data Index: 8544262 (Open Web Text)

Max Activating Token Index: 267

Text #5

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.8028. Min Act: -0.1700

Data Index: 1264521 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7465. Min Act: -0.1700

Data Index: 3909052 (Open Web Text)

Max Activating Token Index: 923

Text #7

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7361. Min Act: -0.1700

Data Index: 3149550 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7287. Min Act: -0.1700

Data Index: 511740 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7168. Min Act: -0.1700

Data Index: 7732187 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7077. Min Act: -0.1700

Data Index: 4715495 (Open Web Text)

Max Activating Token Index: 780

Text #11

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7131. Min Act: -0.1700

Data Index: 8607944 (Open Web Text)

Max Activating Token Index: 333

Text #12

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7030. Min Act: -0.1700

Data Index: 1375114 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.6824. Min Act: -0.1700

Data Index: 2573632 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.6970. Min Act: -0.1700

Data Index: 1261438 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7175. Min Act: -0.1700

Data Index: 6642750 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7085. Min Act: -0.1700

Data Index: 1003818 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.6924. Min Act: -0.1700

Data Index: 254641 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.7087. Min Act: -0.1700

Data Index: 970782 (Open Web Text)

Max Activating Token Index: 201

Text #19

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.6863. Min Act: -0.1700

Data Index: 2004380 (Open Web Text)

Max Activating Token Index: 341