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

Dataset: Open Web Text

Neuron 422 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: 1.1217. Min Range: -1.1217

Max Act: 1.1217. Min Act: -0.1611

Data Index: 3322578 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0949. Min Act: -0.1686

Data Index: 6206076 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0848. Min Act: -0.1695

Data Index: 8804765 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0844. Min Act: -0.1656

Data Index: 4248553 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0798. Min Act: -0.1700

Data Index: 5750587 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0816. Min Act: -0.1639

Data Index: 5106662 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0654. Min Act: -0.1690

Data Index: 3790973 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0618. Min Act: -0.1699

Data Index: 7859510 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0550. Min Act: -0.1687

Data Index: 4285432 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0499. Min Act: -0.1674

Data Index: 3555701 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0478. Min Act: -0.1678

Data Index: 1295997 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0520. Min Act: -0.1674

Data Index: 6516675 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0495. Min Act: -0.1671

Data Index: 4180642 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0437. Min Act: -0.1616

Data Index: 8680073 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0384. Min Act: -0.1676

Data Index: 7943742 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0451. Min Act: -0.1618

Data Index: 1814870 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0353. Min Act: -0.1651

Data Index: 1892066 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0352. Min Act: -0.1687

Data Index: 436790 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0347. Min Act: -0.1680

Data Index: 8027545 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0345. Min Act: -0.1695

Data Index: 3329866 (Open Web Text)

Max Activating Token Index: 1021