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

Dataset: Open Web Text

Neuron 1498 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: 3.1596. Min Range: -3.1596

Max Act: 3.1596. Min Act: -0.1700

Data Index: 209290 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0247. Min Act: -0.1700

Data Index: 1134902 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0259. Min Act: -0.1700

Data Index: 4599539 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.9982. Min Act: -0.1700

Data Index: 6293914 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.9225. Min Act: -0.1700

Data Index: 7909497 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.9061. Min Act: -0.1700

Data Index: 4518906 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8827. Min Act: -0.1700

Data Index: 4204583 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8953. Min Act: -0.1700

Data Index: 3606251 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8471. Min Act: -0.1700

Data Index: 7211722 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8745. Min Act: -0.1700

Data Index: 4295952 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.9063. Min Act: -0.1700

Data Index: 1262664 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8692. Min Act: -0.1700

Data Index: 1648798 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8156. Min Act: -0.1700

Data Index: 5462511 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8524. Min Act: -0.1700

Data Index: 5077551 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8127. Min Act: -0.1700

Data Index: 3686153 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8971. Min Act: -0.1700

Data Index: 1908849 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8232. Min Act: -0.1700

Data Index: 3074457 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8645. Min Act: -0.1700

Data Index: 389327 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8451. Min Act: -0.1700

Data Index: 6298451 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.1596. Min Range: -3.1596

Max Act: 2.8787. Min Act: -0.1700

Data Index: 4405692 (Open Web Text)

Max Activating Token Index: 1023