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

Dataset: Open Web Text

Neuron 2581 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: 1.4419. Min Range: -1.4419

Max Act: 1.4419. Min Act: -0.1679

Data Index: 6466946 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4163. Min Act: -0.1687

Data Index: 7136290 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4143. Min Act: -0.1675

Data Index: 926394 (Open Web Text)

Max Activating Token Index: 622

Text #3

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4094. Min Act: -0.1643

Data Index: 7864127 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4096. Min Act: -0.1622

Data Index: 6544803 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4105. Min Act: -0.1627

Data Index: 3493269 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4185. Min Act: -0.1402

Data Index: 7064817 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4247. Min Act: -0.1666

Data Index: 3294780 (Open Web Text)

Max Activating Token Index: 1003

Text #8

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3882. Min Act: -0.1585

Data Index: 3668 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3924. Min Act: -0.1569

Data Index: 798094 (Open Web Text)

Max Activating Token Index: 1009

Text #10

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3985. Min Act: -0.1651

Data Index: 4878128 (Open Web Text)

Max Activating Token Index: 623

Text #11

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4050. Min Act: -0.1697

Data Index: 663842 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3958. Min Act: -0.1697

Data Index: 7713610 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3925. Min Act: -0.1653

Data Index: 8391913 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3797. Min Act: -0.1647

Data Index: 3028232 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3806. Min Act: -0.1641

Data Index: 26173 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3744. Min Act: -0.1578

Data Index: 6027594 (Open Web Text)

Max Activating Token Index: 221

Text #17

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3836. Min Act: -0.1486

Data Index: 8712232 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3796. Min Act: -0.1643

Data Index: 7832567 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3788. Min Act: -0.1581

Data Index: 2840477 (Open Web Text)

Max Activating Token Index: 66