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

Dataset: Open Web Text

Neuron 824 in Layer 2

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: 2.0896. Min Range: -2.0896

Max Act: 2.0896. Min Act: -0.1700

Data Index: 86970 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.9465. Min Act: -0.1700

Data Index: 900108 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.8383. Min Act: -0.1700

Data Index: 8322708 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7891. Min Act: -0.1700

Data Index: 4235404 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7484. Min Act: -0.1700

Data Index: 4877902 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7712. Min Act: -0.1700

Data Index: 8305130 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7358. Min Act: -0.1700

Data Index: 4593690 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7439. Min Act: -0.1700

Data Index: 2559610 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7105. Min Act: -0.1700

Data Index: 1631858 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6957. Min Act: -0.1700

Data Index: 7844847 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7124. Min Act: -0.1700

Data Index: 4025802 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6883. Min Act: -0.1700

Data Index: 2982091 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.7013. Min Act: -0.1700

Data Index: 8067748 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6529. Min Act: -0.1700

Data Index: 4176132 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6781. Min Act: -0.1700

Data Index: 5356777 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.5908. Min Act: -0.1700

Data Index: 7156082 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6375. Min Act: -0.1700

Data Index: 2525319 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6306. Min Act: -0.1700

Data Index: 6071662 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6180. Min Act: -0.1700

Data Index: 8325647 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.0896. Min Range: -2.0896

Max Act: 1.6279. Min Act: -0.1700

Data Index: 8470228 (Open Web Text)

Max Activating Token Index: 1023