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

Dataset: Open Web Text

Neuron 1103 in Layer 4

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: 4.7066. Min Range: -4.7066

Max Act: 4.7066. Min Act: -0.1700

Data Index: 7846396 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.5779. Min Act: -0.1700

Data Index: 3893346 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.5953. Min Act: -0.1700

Data Index: 6254493 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.5720. Min Act: -0.1700

Data Index: 537256 (Open Web Text)

Max Activating Token Index: 306

Text #4

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.5597. Min Act: -0.1700

Data Index: 4587155 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.5580. Min Act: -0.1700

Data Index: 534541 (Open Web Text)

Max Activating Token Index: 907

Text #6

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4927. Min Act: -0.1700

Data Index: 604433 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4946. Min Act: -0.1700

Data Index: 3114129 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4952. Min Act: -0.1700

Data Index: 4591982 (Open Web Text)

Max Activating Token Index: 81

Text #9

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4992. Min Act: -0.1700

Data Index: 7659906 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.5044. Min Act: -0.1700

Data Index: 322231 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4729. Min Act: -0.1700

Data Index: 4305202 (Open Web Text)

Max Activating Token Index: 812

Text #12

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4623. Min Act: -0.1700

Data Index: 3038309 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4104. Min Act: -0.1700

Data Index: 2512976 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4388. Min Act: -0.1700

Data Index: 7427027 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4329. Min Act: -0.1700

Data Index: 1894742 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4038. Min Act: -0.1700

Data Index: 3015716 (Open Web Text)

Max Activating Token Index: 774

Text #17

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4138. Min Act: -0.1700

Data Index: 8036718 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.3763. Min Act: -0.1700

Data Index: 4166344 (Open Web Text)

Max Activating Token Index: 376

Text #19

Max Range: 4.7066. Min Range: -4.7066

Max Act: 4.4071. Min Act: -0.1700

Data Index: 6564739 (Open Web Text)

Max Activating Token Index: 582