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

Dataset: Open Web Text

Neuron 670 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: 3.1148. Min Range: -3.1148

Max Act: 3.1139. Min Act: -0.1700

Data Index: 4340493 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.1148. Min Act: -0.1700

Data Index: 902043 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0845. Min Act: -0.1700

Data Index: 7434404 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0845. Min Act: -0.1700

Data Index: 8276803 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0845. Min Act: -0.1700

Data Index: 2324122 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0953. Min Act: -0.1700

Data Index: 4368798 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0845. Min Act: -0.1700

Data Index: 4733470 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0899. Min Act: -0.1700

Data Index: 4189597 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0845. Min Act: -0.1700

Data Index: 776187 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0665. Min Act: -0.1700

Data Index: 7872880 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0860. Min Act: -0.1700

Data Index: 1398831 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0704. Min Act: -0.1700

Data Index: 73471 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0734. Min Act: -0.1700

Data Index: 5327576 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0713. Min Act: -0.1700

Data Index: 2414199 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0506. Min Act: -0.1700

Data Index: 1623813 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0389. Min Act: -0.1700

Data Index: 5500864 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0344. Min Act: -0.1700

Data Index: 3469083 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1873744 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0353. Min Act: -0.1700

Data Index: 4521961 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.1148. Min Range: -3.1148

Max Act: 3.0438. Min Act: -0.1700

Data Index: 4242841 (Open Web Text)

Max Activating Token Index: 7