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

Dataset: Open Web Text

Neuron 982 in Layer 3

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: 4.5739. Min Range: -4.5739

Max Act: 4.5739. Min Act: -0.1700

Data Index: 5829003 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.5561. Min Act: -0.1700

Data Index: 8243391 (Open Web Text)

Max Activating Token Index: 815

Text #2

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.3613. Min Act: -0.1700

Data Index: 5010853 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.3355. Min Act: -0.1700

Data Index: 1909959 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.1868. Min Act: -0.1700

Data Index: 595628 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.2501. Min Act: -0.1700

Data Index: 3027381 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.1729. Min Act: -0.1700

Data Index: 5910616 (Open Web Text)

Max Activating Token Index: 404

Text #7

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.0835. Min Act: -0.1700

Data Index: 3064473 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.0753. Min Act: -0.1700

Data Index: 2931842 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.1074. Min Act: -0.1700

Data Index: 8652877 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9763. Min Act: -0.1700

Data Index: 5381715 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.0002. Min Act: -0.1700

Data Index: 7358809 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.0048. Min Act: -0.1700

Data Index: 3993939 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.0447. Min Act: -0.1700

Data Index: 294910 (Open Web Text)

Max Activating Token Index: 772

Text #14

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9654. Min Act: -0.1700

Data Index: 6249718 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9737. Min Act: -0.1700

Data Index: 6077392 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9418. Min Act: -0.1700

Data Index: 143495 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9835. Min Act: -0.1700

Data Index: 1307962 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9845. Min Act: -0.1700

Data Index: 1648796 (Open Web Text)

Max Activating Token Index: 971

Text #19

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9441. Min Act: -0.1700

Data Index: 5281768 (Open Web Text)

Max Activating Token Index: 833