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

Dataset: Open Web Text

Neuron 547 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: 4.3063. Min Range: -4.3063

Max Act: 4.3063. Min Act: -0.1700

Data Index: 2367286 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2856. Min Act: -0.1700

Data Index: 8631036 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2516. Min Act: -0.1700

Data Index: 5618979 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2753. Min Act: -0.1700

Data Index: 5678487 (Open Web Text)

Max Activating Token Index: 424

Text #4

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2358. Min Act: -0.1700

Data Index: 5080637 (Open Web Text)

Max Activating Token Index: 866

Text #5

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2150. Min Act: -0.1700

Data Index: 878940 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2030. Min Act: -0.1700

Data Index: 547389 (Open Web Text)

Max Activating Token Index: 437

Text #7

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.2163. Min Act: -0.1700

Data Index: 6853512 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1913. Min Act: -0.1700

Data Index: 5341083 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1972. Min Act: -0.1700

Data Index: 7987293 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1732. Min Act: -0.1700

Data Index: 2555340 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1452. Min Act: -0.1700

Data Index: 7460525 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1616. Min Act: -0.1700

Data Index: 4290630 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1422. Min Act: -0.1700

Data Index: 6837263 (Open Web Text)

Max Activating Token Index: 779

Text #14

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.0979. Min Act: -0.1700

Data Index: 3895954 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.0826. Min Act: -0.1700

Data Index: 4563080 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1060. Min Act: -0.1700

Data Index: 5279670 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.1071. Min Act: -0.1700

Data Index: 7141465 (Open Web Text)

Max Activating Token Index: 595

Text #18

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.0838. Min Act: -0.1700

Data Index: 6743030 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 4.3063. Min Range: -4.3063

Max Act: 4.0664. Min Act: -0.1700

Data Index: 6128572 (Open Web Text)

Max Activating Token Index: 947