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

Dataset: Open Web Text

Neuron 416 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: 1.1096. Min Range: -1.1096

Max Act: 1.1090. Min Act: -0.1394

Data Index: 3431169 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.1404

Data Index: 5819431 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0989. Min Act: -0.1218

Data Index: 2005561 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0959. Min Act: -0.1152

Data Index: 4477147 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0880. Min Act: -0.1383

Data Index: 3756696 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0780. Min Act: -0.1366

Data Index: 1197047 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0709. Min Act: -0.1371

Data Index: 7308199 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0698. Min Act: -0.1321

Data Index: 8311365 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0648. Min Act: -0.1435

Data Index: 5554477 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0637. Min Act: -0.1374

Data Index: 4452693 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0607. Min Act: -0.1468

Data Index: 8817907 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0642. Min Act: -0.1472

Data Index: 5792373 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0571. Min Act: -0.1395

Data Index: 8791483 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0581. Min Act: -0.1243

Data Index: 2618253 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0482. Min Act: -0.1350

Data Index: 4388103 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0564. Min Act: -0.1250

Data Index: 7462380 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0548. Min Act: -0.1255

Data Index: 6486080 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0461. Min Act: -0.1256

Data Index: 2222022 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0504. Min Act: -0.1333

Data Index: 4735655 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0471. Min Act: -0.1331

Data Index: 4175682 (Open Web Text)

Max Activating Token Index: 1023