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

Dataset: Open Web Text

Neuron 2185 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: 4.2213. Min Range: -4.2213

Max Act: 4.2213. Min Act: -0.1700

Data Index: 121929 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.1651. Min Act: -0.1699

Data Index: 8807991 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.1234. Min Act: -0.1700

Data Index: 1064962 (Open Web Text)

Max Activating Token Index: 293

Text #3

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.1245. Min Act: -0.1700

Data Index: 4879838 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.1489. Min Act: -0.1700

Data Index: 7501202 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0945. Min Act: -0.1700

Data Index: 8158721 (Open Web Text)

Max Activating Token Index: 24

Text #6

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0873. Min Act: -0.1700

Data Index: 8228159 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0601. Min Act: -0.1700

Data Index: 7097356 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0626. Min Act: -0.1700

Data Index: 4875127 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0759. Min Act: -0.1700

Data Index: 1395391 (Open Web Text)

Max Activating Token Index: 785

Text #10

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0787. Min Act: -0.1700

Data Index: 6635320 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0486. Min Act: -0.1700

Data Index: 4659544 (Open Web Text)

Max Activating Token Index: 292

Text #12

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0699. Min Act: -0.1700

Data Index: 2090354 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0237. Min Act: -0.1700

Data Index: 1876906 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0919. Min Act: -0.1700

Data Index: 6979310 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0163. Min Act: -0.1700

Data Index: 2343480 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0226. Min Act: -0.1700

Data Index: 2452118 (Open Web Text)

Max Activating Token Index: 283

Text #17

Max Range: 4.2213. Min Range: -4.2213

Max Act: 3.9981. Min Act: -0.1700

Data Index: 6150673 (Open Web Text)

Max Activating Token Index: 377

Text #18

Max Range: 4.2213. Min Range: -4.2213

Max Act: 4.0030. Min Act: -0.1700

Data Index: 6221057 (Open Web Text)

Max Activating Token Index: 940

Text #19

Max Range: 4.2213. Min Range: -4.2213

Max Act: 3.9939. Min Act: -0.1700

Data Index: 4069027 (Open Web Text)

Max Activating Token Index: 18