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

Dataset: Open Web Text

Neuron 201 in Layer 1

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: 1.7827. Min Range: -1.7827

Max Act: 1.7827. Min Act: -0.1700

Data Index: 3811872 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7685. Min Act: -0.1700

Data Index: 4143916 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7331. Min Act: -0.1700

Data Index: 2859201 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7250. Min Act: -0.1700

Data Index: 765013 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7177. Min Act: -0.1700

Data Index: 6608110 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7167. Min Act: -0.1700

Data Index: 2601787 (Open Web Text)

Max Activating Token Index: 308

Text #6

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7148. Min Act: -0.1700

Data Index: 7519674 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7160. Min Act: -0.1700

Data Index: 3807539 (Open Web Text)

Max Activating Token Index: 634

Text #8

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7247. Min Act: -0.1694

Data Index: 7715208 (Open Web Text)

Max Activating Token Index: 158

Text #9

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7155. Min Act: -0.1700

Data Index: 5835580 (Open Web Text)

Max Activating Token Index: 415

Text #10

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7128. Min Act: -0.1700

Data Index: 4728908 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7095. Min Act: -0.1700

Data Index: 8193591 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7003. Min Act: -0.1700

Data Index: 8343889 (Open Web Text)

Max Activating Token Index: 144

Text #13

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7108. Min Act: -0.1700

Data Index: 6038992 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.7000. Min Act: -0.1700

Data Index: 2247862 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.6849. Min Act: -0.1700

Data Index: 3943633 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.6895. Min Act: -0.1700

Data Index: 8754830 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.6946. Min Act: -0.1700

Data Index: 2205089 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.6800. Min Act: -0.1700

Data Index: 5400209 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 1.7827. Min Range: -1.7827

Max Act: 1.6733. Min Act: -0.1700

Data Index: 1029231 (Open Web Text)

Max Activating Token Index: 440