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

Dataset: Open Web Text

Neuron 455 in Layer 6

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: 4.3220. Min Range: -4.3220

Max Act: 4.3220. Min Act: -0.1700

Data Index: 5653882 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1918. Min Act: -0.1700

Data Index: 8180333 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.2221. Min Act: -0.1700

Data Index: 6026437 (Open Web Text)

Max Activating Token Index: 162

Text #3

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1644. Min Act: -0.1700

Data Index: 5005197 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1533. Min Act: -0.1700

Data Index: 574687 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1072. Min Act: -0.1700

Data Index: 6814444 (Open Web Text)

Max Activating Token Index: 532

Text #6

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1008. Min Act: -0.1700

Data Index: 4388303 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1030. Min Act: -0.1700

Data Index: 7495888 (Open Web Text)

Max Activating Token Index: 474

Text #8

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1102. Min Act: -0.1700

Data Index: 5335426 (Open Web Text)

Max Activating Token Index: 161

Text #9

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1270. Min Act: -0.1700

Data Index: 6016954 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.1054. Min Act: -0.1700

Data Index: 5655768 (Open Web Text)

Max Activating Token Index: 99

Text #11

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0678. Min Act: -0.1700

Data Index: 10110 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0843. Min Act: -0.1700

Data Index: 6267452 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0423. Min Act: -0.1700

Data Index: 4473266 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0910. Min Act: -0.1700

Data Index: 5337988 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0698. Min Act: -0.1700

Data Index: 7269796 (Open Web Text)

Max Activating Token Index: 728

Text #16

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0488. Min Act: -0.1700

Data Index: 451340 (Open Web Text)

Max Activating Token Index: 646

Text #17

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0336. Min Act: -0.1700

Data Index: 3115884 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0376. Min Act: -0.1700

Data Index: 4908592 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.0058. Min Act: -0.1700

Data Index: 623830 (Open Web Text)

Max Activating Token Index: 437