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

Dataset: Open Web Text

Neuron 874 in Layer 3

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: 3.3567. Min Range: -3.3567

Max Act: 3.3567. Min Act: -0.1700

Data Index: 7335076 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2838. Min Act: -0.1700

Data Index: 3930837 (Open Web Text)

Max Activating Token Index: 926

Text #2

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.3083. Min Act: -0.1700

Data Index: 4950965 (Open Web Text)

Max Activating Token Index: 181

Text #3

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2692. Min Act: -0.1700

Data Index: 3621142 (Open Web Text)

Max Activating Token Index: 884

Text #4

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2166. Min Act: -0.1700

Data Index: 8019662 (Open Web Text)

Max Activating Token Index: 625

Text #5

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2300. Min Act: -0.1700

Data Index: 1530971 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2177. Min Act: -0.1700

Data Index: 4985731 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2060. Min Act: -0.1700

Data Index: 7770312 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1886. Min Act: -0.1700

Data Index: 5962312 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1897. Min Act: -0.1700

Data Index: 8160450 (Open Web Text)

Max Activating Token Index: 907

Text #10

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1328. Min Act: -0.1700

Data Index: 4314164 (Open Web Text)

Max Activating Token Index: 869

Text #11

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1356. Min Act: -0.1700

Data Index: 3807193 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1547. Min Act: -0.1700

Data Index: 6164902 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1640. Min Act: -0.1700

Data Index: 7627763 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1153. Min Act: -0.1700

Data Index: 8165426 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1116. Min Act: -0.1700

Data Index: 4869406 (Open Web Text)

Max Activating Token Index: 291

Text #16

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.0771. Min Act: -0.1700

Data Index: 3635645 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.0987. Min Act: -0.1700

Data Index: 3275052 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.1059. Min Act: -0.1700

Data Index: 5992371 (Open Web Text)

Max Activating Token Index: 97

Text #19

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.0900. Min Act: -0.1700

Data Index: 6029772 (Open Web Text)

Max Activating Token Index: 337