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

Dataset: Open Web Text

Neuron 219 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: 2.5311. Min Range: -2.5311

Max Act: 2.5311. Min Act: -0.1700

Data Index: 8591775 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4569. Min Act: -0.1700

Data Index: 1198099 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4377. Min Act: -0.1700

Data Index: 3225235 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4213. Min Act: -0.1700

Data Index: 6583129 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4062. Min Act: -0.1700

Data Index: 3618850 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4007. Min Act: -0.1700

Data Index: 5680872 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4173. Min Act: -0.1700

Data Index: 7105615 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3968. Min Act: -0.1700

Data Index: 8060815 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3993. Min Act: -0.1700

Data Index: 2223084 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3927. Min Act: -0.1700

Data Index: 6238015 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4027. Min Act: -0.1700

Data Index: 4653808 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3909. Min Act: -0.1700

Data Index: 2398184 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3909. Min Act: -0.1700

Data Index: 2430114 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3780. Min Act: -0.1700

Data Index: 1984548 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3804. Min Act: -0.1700

Data Index: 3748558 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3582. Min Act: -0.1700

Data Index: 4559996 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3617. Min Act: -0.1700

Data Index: 5336292 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3683. Min Act: -0.1700

Data Index: 2758923 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3634. Min Act: -0.1700

Data Index: 6968915 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.3599. Min Act: -0.1700

Data Index: 6674859 (Open Web Text)

Max Activating Token Index: 2