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

Dataset: Open Web Text

Neuron 1285 in Layer 1

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: 1.3737. Min Range: -1.3737

Max Act: 1.3737. Min Act: -0.1699

Data Index: 8818102 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.3405. Min Act: -0.1658

Data Index: 6996621 (Open Web Text)

Max Activating Token Index: 947

Text #2

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2902. Min Act: -0.1689

Data Index: 6880409 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2849. Min Act: -0.1634

Data Index: 1332227 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2882. Min Act: -0.1698

Data Index: 3921474 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2925. Min Act: -0.1700

Data Index: 7072769 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2903. Min Act: -0.1691

Data Index: 1420279 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2776. Min Act: -0.1700

Data Index: 1189407 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2809. Min Act: -0.1691

Data Index: 6996622 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2782. Min Act: -0.1672

Data Index: 523224 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2744. Min Act: -0.1700

Data Index: 6619501 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2654. Min Act: -0.1531

Data Index: 8510216 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2608. Min Act: -0.1699

Data Index: 4784680 (Open Web Text)

Max Activating Token Index: 989

Text #13

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2628. Min Act: -0.1697

Data Index: 8318495 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2630. Min Act: -0.1693

Data Index: 1720402 (Open Web Text)

Max Activating Token Index: 231

Text #15

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2600. Min Act: -0.1698

Data Index: 476033 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2582. Min Act: -0.1697

Data Index: 4097243 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2441. Min Act: -0.1695

Data Index: 7796702 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2435. Min Act: -0.1698

Data Index: 2897411 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2470. Min Act: -0.1653

Data Index: 4433152 (Open Web Text)

Max Activating Token Index: 15