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

Dataset: Open Web Text

Neuron 2199 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: 2.1062. Min Range: -2.1062

Max Act: 2.1062. Min Act: -0.1700

Data Index: 203503 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.1062. Min Range: -2.1062

Max Act: 2.1050. Min Act: -0.1700

Data Index: 532327 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.1062. Min Range: -2.1062

Max Act: 2.0916. Min Act: -0.1700

Data Index: 4185110 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.1062. Min Range: -2.1062

Max Act: 2.0509. Min Act: -0.1700

Data Index: 2633506 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.1062. Min Range: -2.1062

Max Act: 2.0389. Min Act: -0.1700

Data Index: 2874010 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.1062. Min Range: -2.1062

Max Act: 2.0035. Min Act: -0.1700

Data Index: 1302712 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.1062. Min Range: -2.1062

Max Act: 2.0223. Min Act: -0.1700

Data Index: 4774030 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9491. Min Act: -0.1700

Data Index: 3776864 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9904. Min Act: -0.1700

Data Index: 6798771 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9913. Min Act: -0.1700

Data Index: 8560095 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9534. Min Act: -0.1700

Data Index: 4867119 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9316. Min Act: -0.1700

Data Index: 2798252 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9351. Min Act: -0.1700

Data Index: 3959625 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9013. Min Act: -0.1700

Data Index: 4131911 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9146. Min Act: -0.1700

Data Index: 1180620 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9223. Min Act: -0.1700

Data Index: 4353012 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9009. Min Act: -0.1700

Data Index: 3078795 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9161. Min Act: -0.1700

Data Index: 5326398 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.9019. Min Act: -0.1700

Data Index: 7276232 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.1062. Min Range: -2.1062

Max Act: 1.8781. Min Act: -0.1700

Data Index: 5368325 (Open Web Text)

Max Activating Token Index: 1023