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

Dataset: Open Web Text

Neuron 2702 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: 2.0195. Min Range: -2.0195

Max Act: 2.0195. Min Act: -0.1246

Data Index: 546723 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.0195. Min Range: -2.0195

Max Act: 2.0037. Min Act: -0.1424

Data Index: 6815723 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.0195. Min Range: -2.0195

Max Act: 2.0134. Min Act: -0.1408

Data Index: 7521926 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9560. Min Act: -0.1206

Data Index: 51456 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9619. Min Act: -0.1528

Data Index: 1761412 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9427. Min Act: -0.1158

Data Index: 6283139 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9359. Min Act: -0.1308

Data Index: 2624780 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9545. Min Act: -0.1653

Data Index: 3249497 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9297. Min Act: -0.1175

Data Index: 3572163 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9317. Min Act: -0.1300

Data Index: 7391482 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9213. Min Act: -0.1414

Data Index: 5091835 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9118. Min Act: -0.1540

Data Index: 4998403 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9192. Min Act: -0.1030

Data Index: 1711444 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9192. Min Act: -0.1241

Data Index: 2243992 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9231. Min Act: -0.1472

Data Index: 3115171 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9013. Min Act: -0.1379

Data Index: 7427511 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9179. Min Act: -0.1148

Data Index: 3872338 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9006. Min Act: -0.1326

Data Index: 1734322 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.8999. Min Act: -0.1193

Data Index: 2476909 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.9219. Min Act: -0.1049

Data Index: 1238504 (Open Web Text)

Max Activating Token Index: 1023