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

Dataset: Open Web Text

Neuron 856 in Layer 0

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: 4.2797. Min Range: -4.2797

Max Act: 4.2797. Min Act: -0.1700

Data Index: 5564080 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.2086. Min Act: -0.1700

Data Index: 2281168 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.2100. Min Act: -0.1700

Data Index: 8830212 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1702. Min Act: -0.1700

Data Index: 6922104 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1623. Min Act: -0.1700

Data Index: 4257821 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1726. Min Act: -0.1700

Data Index: 1780931 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1496. Min Act: -0.1700

Data Index: 3103059 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1291. Min Act: -0.1700

Data Index: 8802763 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1373. Min Act: -0.1700

Data Index: 8057082 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1037. Min Act: -0.1700

Data Index: 1165311 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0993. Min Act: -0.1700

Data Index: 1994463 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1067. Min Act: -0.1700

Data Index: 4255497 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1149. Min Act: -0.1700

Data Index: 6109732 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0987. Min Act: -0.1700

Data Index: 8333839 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1339. Min Act: -0.1700

Data Index: 7918124 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1126. Min Act: -0.1700

Data Index: 7504729 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0974. Min Act: -0.1700

Data Index: 4760105 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1022. Min Act: -0.1700

Data Index: 6535429 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0835. Min Act: -0.1700

Data Index: 8412405 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0884. Min Act: -0.1700

Data Index: 8513643 (Open Web Text)

Max Activating Token Index: 3