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

Dataset: Open Web Text

Neuron 12 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: 3.5741. Min Range: -3.5741

Max Act: 3.5741. Min Act: -0.1700

Data Index: 4970400 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.5542. Min Act: -0.1700

Data Index: 8152325 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.5152. Min Act: -0.1700

Data Index: 7027757 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.5131. Min Act: -0.1700

Data Index: 4770598 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4888. Min Act: -0.1700

Data Index: 4713478 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4795. Min Act: -0.1700

Data Index: 3445708 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4835. Min Act: -0.1700

Data Index: 6711167 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4703. Min Act: -0.1700

Data Index: 7391103 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4674. Min Act: -0.1700

Data Index: 8658945 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4575. Min Act: -0.1700

Data Index: 8493901 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4489. Min Act: -0.1700

Data Index: 3145089 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4331. Min Act: -0.1700

Data Index: 7336276 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4363. Min Act: -0.1700

Data Index: 4546906 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4155. Min Act: -0.1700

Data Index: 5692261 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4138. Min Act: -0.1700

Data Index: 5095945 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4181. Min Act: -0.1700

Data Index: 6894579 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4253. Min Act: -0.1700

Data Index: 6638730 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4219. Min Act: -0.1700

Data Index: 7762785 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4058. Min Act: -0.1700

Data Index: 5125612 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.5741. Min Range: -3.5741

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1882076 (Open Web Text)

Max Activating Token Index: 13