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

Dataset: Open Web Text

Neuron 2432 in Layer 1

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: 2.0032. Min Range: -2.0032

Max Act: 2.0032. Min Act: -0.1700

Data Index: 2299836 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9820. Min Act: -0.1700

Data Index: 6782292 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9644. Min Act: -0.1700

Data Index: 8338543 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9410. Min Act: -0.1700

Data Index: 2023354 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9516. Min Act: -0.1700

Data Index: 3963186 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9353. Min Act: -0.1700

Data Index: 7560852 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9369. Min Act: -0.1700

Data Index: 3855090 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9422. Min Act: -0.1700

Data Index: 5231805 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9187. Min Act: -0.1700

Data Index: 6312943 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9090. Min Act: -0.1700

Data Index: 5410359 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9189. Min Act: -0.1699

Data Index: 7560855 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9165. Min Act: -0.1700

Data Index: 3511088 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9149. Min Act: -0.1700

Data Index: 7560854 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9238. Min Act: -0.1700

Data Index: 3568620 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9052. Min Act: -0.1700

Data Index: 243614 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9216. Min Act: -0.1700

Data Index: 5231806 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.9062. Min Act: -0.1700

Data Index: 3797050 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.8965. Min Act: -0.1700

Data Index: 5967274 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.8972. Min Act: -0.1700

Data Index: 1037546 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.0032. Min Range: -2.0032

Max Act: 1.8856. Min Act: -0.1700

Data Index: 7312916 (Open Web Text)

Max Activating Token Index: 247