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

Dataset: Open Web Text

Neuron 81 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: 5.1977. Min Range: -5.1977

Max Act: 5.1795. Min Act: -0.1700

Data Index: 227645 (Open Web Text)

Max Activating Token Index: 966

Text #1

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1863. Min Act: -0.1700

Data Index: 901787 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1977. Min Act: -0.1700

Data Index: 7121134 (Open Web Text)

Max Activating Token Index: 896

Text #3

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1739. Min Act: -0.1700

Data Index: 6814083 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1785. Min Act: -0.1700

Data Index: 6744743 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1812. Min Act: -0.1700

Data Index: 2117817 (Open Web Text)

Max Activating Token Index: 88

Text #6

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1460. Min Act: -0.1700

Data Index: 2363180 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1365. Min Act: -0.1700

Data Index: 6398278 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1560. Min Act: -0.1700

Data Index: 7463860 (Open Web Text)

Max Activating Token Index: 703

Text #9

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1133. Min Act: -0.1700

Data Index: 2527829 (Open Web Text)

Max Activating Token Index: 884

Text #10

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1102. Min Act: -0.1700

Data Index: 7899195 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1071. Min Act: -0.1700

Data Index: 90403 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1433. Min Act: -0.1700

Data Index: 7533908 (Open Web Text)

Max Activating Token Index: 967

Text #13

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1116. Min Act: -0.1700

Data Index: 2255319 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.0637. Min Act: -0.1700

Data Index: 556315 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.0951. Min Act: -0.1700

Data Index: 4962386 (Open Web Text)

Max Activating Token Index: 835

Text #16

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.0699. Min Act: -0.1700

Data Index: 4916615 (Open Web Text)

Max Activating Token Index: 764

Text #17

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.0997. Min Act: -0.1700

Data Index: 1566771 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1049. Min Act: -0.1700

Data Index: 5001052 (Open Web Text)

Max Activating Token Index: 328

Text #19

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1236. Min Act: -0.1700

Data Index: 5924142 (Open Web Text)

Max Activating Token Index: 900