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

Dataset: Open Web Text

Neuron 1330 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: 2.3690. Min Range: -2.3690

Max Act: 2.3690. Min Act: -0.1700

Data Index: 5100290 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.3337. Min Act: -0.1700

Data Index: 7515676 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2831. Min Act: -0.1700

Data Index: 6212126 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2939. Min Act: -0.1700

Data Index: 5931341 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2581. Min Act: -0.1700

Data Index: 3108558 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2721. Min Act: -0.1700

Data Index: 3278138 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2442. Min Act: -0.1700

Data Index: 2219596 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2387. Min Act: -0.1700

Data Index: 1595041 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1891. Min Act: -0.1700

Data Index: 4059993 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2109. Min Act: -0.1700

Data Index: 4107872 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.2001. Min Act: -0.1700

Data Index: 215418 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1841. Min Act: -0.1700

Data Index: 3999136 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1760. Min Act: -0.1700

Data Index: 7053179 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1728. Min Act: -0.1700

Data Index: 891400 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1276. Min Act: -0.1700

Data Index: 1284716 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1414. Min Act: -0.1700

Data Index: 5642005 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1076. Min Act: -0.1700

Data Index: 2238152 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1398. Min Act: -0.1700

Data Index: 347350 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1058. Min Act: -0.1700

Data Index: 5875019 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.3690. Min Range: -2.3690

Max Act: 2.1331. Min Act: -0.1700

Data Index: 6756875 (Open Web Text)

Max Activating Token Index: 1023