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

Dataset: Open Web Text

Neuron 992 in Layer 3

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: 4.3785. Min Range: -4.3785

Max Act: 4.3785. Min Act: -0.1700

Data Index: 7470683 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1967. Min Act: -0.1700

Data Index: 882665 (Open Web Text)

Max Activating Token Index: 173

Text #2

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.2062. Min Act: -0.1700

Data Index: 633724 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.2212. Min Act: -0.1700

Data Index: 882666 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1834. Min Act: -0.1700

Data Index: 1450063 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1609. Min Act: -0.1700

Data Index: 251732 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1781. Min Act: -0.1700

Data Index: 1450072 (Open Web Text)

Max Activating Token Index: 604

Text #7

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1453. Min Act: -0.1700

Data Index: 973643 (Open Web Text)

Max Activating Token Index: 184

Text #8

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1346. Min Act: -0.1700

Data Index: 6907930 (Open Web Text)

Max Activating Token Index: 293

Text #9

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1253. Min Act: -0.1700

Data Index: 4222284 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1585. Min Act: -0.1700

Data Index: 8641220 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1332. Min Act: -0.1700

Data Index: 2851039 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1044. Min Act: -0.1700

Data Index: 5668189 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1064. Min Act: -0.1700

Data Index: 1450078 (Open Web Text)

Max Activating Token Index: 888

Text #14

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1202. Min Act: -0.1700

Data Index: 5668188 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1072. Min Act: -0.1700

Data Index: 882667 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1105. Min Act: -0.1700

Data Index: 251722 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1176. Min Act: -0.1700

Data Index: 5250023 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.1076. Min Act: -0.1700

Data Index: 2323740 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 4.3785. Min Range: -4.3785

Max Act: 4.0528. Min Act: -0.1700

Data Index: 2851041 (Open Web Text)

Max Activating Token Index: 508