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

Dataset: Open Web Text

Neuron 2024 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: 4.4227. Min Range: -4.4227

Max Act: 4.4227. Min Act: -0.1700

Data Index: 4621599 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.4182. Min Act: -0.1700

Data Index: 7107989 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.3261. Min Act: -0.1700

Data Index: 8008353 (Open Web Text)

Max Activating Token Index: 639

Text #3

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.3012. Min Act: -0.1700

Data Index: 4102456 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.3050. Min Act: -0.1700

Data Index: 7147228 (Open Web Text)

Max Activating Token Index: 790

Text #5

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2793. Min Act: -0.1700

Data Index: 3559619 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.3058. Min Act: -0.1700

Data Index: 3390235 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2644. Min Act: -0.1700

Data Index: 4926894 (Open Web Text)

Max Activating Token Index: 787

Text #8

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2614. Min Act: -0.1700

Data Index: 3099655 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2515. Min Act: -0.1700

Data Index: 6944849 (Open Web Text)

Max Activating Token Index: 216

Text #10

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2403. Min Act: -0.1700

Data Index: 6100793 (Open Web Text)

Max Activating Token Index: 192

Text #11

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1989. Min Act: -0.1700

Data Index: 8472613 (Open Web Text)

Max Activating Token Index: 126

Text #12

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2115. Min Act: -0.1700

Data Index: 2542666 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2131. Min Act: -0.1700

Data Index: 1666429 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2078. Min Act: -0.1700

Data Index: 4511914 (Open Web Text)

Max Activating Token Index: 353

Text #15

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2014. Min Act: -0.1700

Data Index: 7324886 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1956. Min Act: -0.1700

Data Index: 1029674 (Open Web Text)

Max Activating Token Index: 215

Text #17

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1729. Min Act: -0.1700

Data Index: 1277516 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1950. Min Act: -0.1700

Data Index: 4103374 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1945. Min Act: -0.1700

Data Index: 395753 (Open Web Text)

Max Activating Token Index: 798