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

Dataset: Open Web Text

Neuron 1564 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: 4.4415. Min Range: -4.4415

Max Act: 4.4415. Min Act: -0.1700

Data Index: 2135088 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.4178. Min Act: -0.1700

Data Index: 1375202 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.4330. Min Act: -0.1700

Data Index: 1692207 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3905. Min Act: -0.1700

Data Index: 918041 (Open Web Text)

Max Activating Token Index: 60

Text #4

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3954. Min Act: -0.1700

Data Index: 7910101 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3812. Min Act: -0.1700

Data Index: 6004198 (Open Web Text)

Max Activating Token Index: 107

Text #6

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3818. Min Act: -0.1700

Data Index: 55380 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3635. Min Act: -0.1700

Data Index: 6942768 (Open Web Text)

Max Activating Token Index: 449

Text #8

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3447. Min Act: -0.1700

Data Index: 6002753 (Open Web Text)

Max Activating Token Index: 197

Text #9

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3455. Min Act: -0.1700

Data Index: 7260424 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3421. Min Act: -0.1700

Data Index: 3162185 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3316. Min Act: -0.1700

Data Index: 90471 (Open Web Text)

Max Activating Token Index: 198

Text #12

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3637. Min Act: -0.1700

Data Index: 2931032 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3006. Min Act: -0.1700

Data Index: 486213 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.2809. Min Act: -0.1700

Data Index: 1649168 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.2796. Min Act: -0.1700

Data Index: 1355094 (Open Web Text)

Max Activating Token Index: 304

Text #16

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.2731. Min Act: -0.1700

Data Index: 4345537 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.2998. Min Act: -0.1700

Data Index: 4536782 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.2911. Min Act: -0.1700

Data Index: 4757541 (Open Web Text)

Max Activating Token Index: 916

Text #19

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3003. Min Act: -0.1700

Data Index: 1823604 (Open Web Text)

Max Activating Token Index: 555