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

Dataset: Open Web Text

Neuron 1182 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: 3.3086. Min Range: -3.3086

Max Act: 3.2980. Min Act: -0.1700

Data Index: 4650672 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.3086. Min Act: -0.1700

Data Index: 7501489 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2703. Min Act: -0.1700

Data Index: 2105101 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2538. Min Act: -0.1700

Data Index: 4321399 (Open Web Text)

Max Activating Token Index: 220

Text #4

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1956425 (Open Web Text)

Max Activating Token Index: 835

Text #5

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2402. Min Act: -0.1700

Data Index: 657741 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2416. Min Act: -0.1700

Data Index: 7293322 (Open Web Text)

Max Activating Token Index: 907

Text #7

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2276. Min Act: -0.1700

Data Index: 2423929 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2252. Min Act: -0.1700

Data Index: 7714859 (Open Web Text)

Max Activating Token Index: 250

Text #9

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2333. Min Act: -0.1700

Data Index: 4454217 (Open Web Text)

Max Activating Token Index: 284

Text #10

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1972. Min Act: -0.1700

Data Index: 4604116 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2067. Min Act: -0.1700

Data Index: 3399668 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2068. Min Act: -0.1700

Data Index: 3272515 (Open Web Text)

Max Activating Token Index: 406

Text #13

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2049. Min Act: -0.1700

Data Index: 5868363 (Open Web Text)

Max Activating Token Index: 848

Text #14

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2055. Min Act: -0.1700

Data Index: 7763778 (Open Web Text)

Max Activating Token Index: 857

Text #15

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1884. Min Act: -0.1700

Data Index: 5647069 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1857. Min Act: -0.1700

Data Index: 7766094 (Open Web Text)

Max Activating Token Index: 302

Text #17

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1878. Min Act: -0.1700

Data Index: 3355159 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1734. Min Act: -0.1700

Data Index: 3073846 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1769. Min Act: -0.1700

Data Index: 3196172 (Open Web Text)

Max Activating Token Index: 658