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

Dataset: Open Web Text

Neuron 1992 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: 2.4623. Min Range: -2.4623

Max Act: 2.4623. Min Act: -0.1700

Data Index: 2695781 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.4507. Min Act: -0.1700

Data Index: 4064235 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.4316. Min Act: -0.1700

Data Index: 3049601 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.4039. Min Act: -0.1700

Data Index: 2650989 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.4087. Min Act: -0.1700

Data Index: 6001673 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3922. Min Act: -0.1700

Data Index: 3268395 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3947. Min Act: -0.1700

Data Index: 1276270 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.4007. Min Act: -0.1700

Data Index: 7709824 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3854. Min Act: -0.1700

Data Index: 647445 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3787. Min Act: -0.1700

Data Index: 7573903 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3560. Min Act: -0.1700

Data Index: 1742285 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3641. Min Act: -0.1700

Data Index: 3726707 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3448. Min Act: -0.1700

Data Index: 6464920 (Open Web Text)

Max Activating Token Index: 66

Text #13

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3444. Min Act: -0.1700

Data Index: 5116082 (Open Web Text)

Max Activating Token Index: 60

Text #14

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3222. Min Act: -0.1700

Data Index: 1894919 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3185. Min Act: -0.1700

Data Index: 5631774 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3213. Min Act: -0.1700

Data Index: 5080289 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3239. Min Act: -0.1700

Data Index: 6702705 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3236. Min Act: -0.1700

Data Index: 3337325 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 2.4623. Min Range: -2.4623

Max Act: 2.3267. Min Act: -0.1700

Data Index: 2306202 (Open Web Text)

Max Activating Token Index: 47