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

Dataset: Open Web Text

Neuron 2105 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: 2.7724. Min Range: -2.7724

Max Act: 2.7469. Min Act: -0.1700

Data Index: 5473588 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.7724. Min Act: -0.1700

Data Index: 5240700 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.7452. Min Act: -0.1700

Data Index: 3755891 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.7052. Min Act: -0.1700

Data Index: 348803 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6864. Min Act: -0.1700

Data Index: 4186218 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6858. Min Act: -0.1700

Data Index: 6566852 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6632. Min Act: -0.1700

Data Index: 8594759 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6608. Min Act: -0.1700

Data Index: 165826 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6595. Min Act: -0.1700

Data Index: 5284103 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6652. Min Act: -0.1700

Data Index: 5327683 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6582. Min Act: -0.1700

Data Index: 495123 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6430. Min Act: -0.1700

Data Index: 5412792 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6406. Min Act: -0.1700

Data Index: 1521673 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6213. Min Act: -0.1700

Data Index: 3670726 (Open Web Text)

Max Activating Token Index: 940

Text #14

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6369. Min Act: -0.1700

Data Index: 5964960 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6298. Min Act: -0.1700

Data Index: 7107718 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6360. Min Act: -0.1700

Data Index: 7148381 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6243. Min Act: -0.1700

Data Index: 4327034 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6372. Min Act: -0.1700

Data Index: 7532087 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 2.7724. Min Range: -2.7724

Max Act: 2.6080. Min Act: -0.1700

Data Index: 5397614 (Open Web Text)

Max Activating Token Index: 8