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

Dataset: Open Web Text

Neuron 1753 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: 0.1675. Min Range: -0.1675

Max Act: 0.1675. Min Act: -0.1699

Data Index: 865126 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1609. Min Act: -0.1700

Data Index: 1347481 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1478. Min Act: -0.1696

Data Index: 8489815 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1392. Min Act: -0.1700

Data Index: 861051 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1191. Min Act: -0.1700

Data Index: 1163299 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1232. Min Act: -0.1700

Data Index: 4849364 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1191. Min Act: -0.1700

Data Index: 7932004 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1183. Min Act: -0.1700

Data Index: 3108828 (Open Web Text)

Max Activating Token Index: 660

Text #8

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1169. Min Act: -0.1698

Data Index: 583959 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1134. Min Act: -0.1700

Data Index: 8515418 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1148. Min Act: -0.1700

Data Index: 1868160 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1139. Min Act: -0.1700

Data Index: 8612923 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1131. Min Act: -0.1700

Data Index: 8564972 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1047. Min Act: -0.1700

Data Index: 8003776 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1024. Min Act: -0.1700

Data Index: 3476547 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1063. Min Act: -0.1700

Data Index: 5057968 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0988. Min Act: -0.1700

Data Index: 768136 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0959. Min Act: -0.1700

Data Index: 1785212 (Open Web Text)

Max Activating Token Index: 334

Text #18

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0963. Min Act: -0.1700

Data Index: 5282070 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0965. Min Act: -0.1700

Data Index: 4064294 (Open Web Text)

Max Activating Token Index: 920