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

Dataset: Open Web Text

Neuron 1971 in Layer 4

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: 3.3598. Min Range: -3.3598

Max Act: 3.3598. Min Act: -0.1700

Data Index: 4655817 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.3209. Min Act: -0.1700

Data Index: 5519743 (Open Web Text)

Max Activating Token Index: 565

Text #2

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1073477 (Open Web Text)

Max Activating Token Index: 839

Text #3

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.3028. Min Act: -0.1700

Data Index: 482473 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2850. Min Act: -0.1700

Data Index: 938822 (Open Web Text)

Max Activating Token Index: 489

Text #5

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2509. Min Act: -0.1700

Data Index: 297781 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2216. Min Act: -0.1700

Data Index: 2656374 (Open Web Text)

Max Activating Token Index: 293

Text #7

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2259. Min Act: -0.1700

Data Index: 2972347 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.1976. Min Act: -0.1700

Data Index: 6607114 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2214. Min Act: -0.1700

Data Index: 7032787 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2150. Min Act: -0.1700

Data Index: 461661 (Open Web Text)

Max Activating Token Index: 154

Text #11

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2118. Min Act: -0.1700

Data Index: 2258884 (Open Web Text)

Max Activating Token Index: 257

Text #12

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.1970. Min Act: -0.1700

Data Index: 7016774 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2105. Min Act: -0.1700

Data Index: 6294869 (Open Web Text)

Max Activating Token Index: 244

Text #14

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2083. Min Act: -0.1700

Data Index: 6482438 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.1856. Min Act: -0.1700

Data Index: 7810969 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.2082. Min Act: -0.1700

Data Index: 2151218 (Open Web Text)

Max Activating Token Index: 662

Text #17

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.1784. Min Act: -0.1700

Data Index: 5326714 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.1954. Min Act: -0.1700

Data Index: 3115094 (Open Web Text)

Max Activating Token Index: 282

Text #19

Max Range: 3.3598. Min Range: -3.3598

Max Act: 3.1882. Min Act: -0.1700

Data Index: 413699 (Open Web Text)

Max Activating Token Index: 389