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

Dataset: Open Web Text

Neuron 2273 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: 3.9646. Min Range: -3.9646

Max Act: 3.9646. Min Act: -0.1700

Data Index: 4300767 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.9646. Min Act: -0.1700

Data Index: 1175274 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.9318. Min Act: -0.1700

Data Index: 3532414 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.9318. Min Act: -0.1700

Data Index: 6672745 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.9318. Min Act: -0.1700

Data Index: 8647794 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.9340. Min Act: -0.1700

Data Index: 2063100 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1788204 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 688007 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1678954 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8563. Min Act: -0.1700

Data Index: 1077232 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1677646 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1654851 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1556189 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8563. Min Act: -0.1700

Data Index: 1451420 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8563. Min Act: -0.1700

Data Index: 831459 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 161049 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1409606 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 473918 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 1216657 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.8664. Min Act: -0.1700

Data Index: 773134 (Open Web Text)

Max Activating Token Index: 3