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

Dataset: Open Web Text

Neuron 2064 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: 3.5739. Min Range: -3.5739

Max Act: 3.5739. Min Act: -0.1700

Data Index: 6643240 (Open Web Text)

Max Activating Token Index: 140

Text #1

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.5451. Min Act: -0.1700

Data Index: 3285941 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.5379. Min Act: -0.1700

Data Index: 7511665 (Open Web Text)

Max Activating Token Index: 64

Text #3

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.5342. Min Act: -0.1700

Data Index: 5323023 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.5121. Min Act: -0.1700

Data Index: 816019 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.5076. Min Act: -0.1700

Data Index: 7511664 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4557. Min Act: -0.1700

Data Index: 6552991 (Open Web Text)

Max Activating Token Index: 68

Text #7

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4530. Min Act: -0.1700

Data Index: 6660899 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4437. Min Act: -0.1700

Data Index: 1762911 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4436. Min Act: -0.1700

Data Index: 2026408 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4703. Min Act: -0.1700

Data Index: 3723777 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4245. Min Act: -0.1700

Data Index: 3285939 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4232. Min Act: -0.1700

Data Index: 3285942 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4218. Min Act: -0.1700

Data Index: 7511663 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.3970. Min Act: -0.1700

Data Index: 5393961 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4218. Min Act: -0.1700

Data Index: 4670745 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4170. Min Act: -0.1700

Data Index: 816020 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4043. Min Act: -0.1700

Data Index: 7511662 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.4012. Min Act: -0.1700

Data Index: 1845572 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 3.5739. Min Range: -3.5739

Max Act: 3.3867. Min Act: -0.1700

Data Index: 1911124 (Open Web Text)

Max Activating Token Index: 50