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

Dataset: Open Web Text

Neuron 103 in Layer 1

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: 1.6127. Min Range: -1.6127

Max Act: 1.6127. Min Act: -0.1700

Data Index: 5997266 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5546. Min Act: -0.1700

Data Index: 2813161 (Open Web Text)

Max Activating Token Index: 185

Text #2

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5484. Min Act: -0.1700

Data Index: 7126550 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5355. Min Act: -0.1700

Data Index: 4612828 (Open Web Text)

Max Activating Token Index: 1001

Text #4

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5370. Min Act: -0.1700

Data Index: 1565652 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5310. Min Act: -0.1700

Data Index: 4659356 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5254. Min Act: -0.1700

Data Index: 5725503 (Open Web Text)

Max Activating Token Index: 427

Text #7

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5108. Min Act: -0.1700

Data Index: 2383011 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5070. Min Act: -0.1700

Data Index: 4612829 (Open Web Text)

Max Activating Token Index: 109

Text #9

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5088. Min Act: -0.1700

Data Index: 5622210 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5037. Min Act: -0.1700

Data Index: 3331686 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5013. Min Act: -0.1700

Data Index: 977182 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4886. Min Act: -0.1700

Data Index: 6761581 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4978. Min Act: -0.1700

Data Index: 4972575 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4793. Min Act: -0.1700

Data Index: 6154678 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4860. Min Act: -0.1700

Data Index: 3188498 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4812. Min Act: -0.1700

Data Index: 4693935 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4772. Min Act: -0.1700

Data Index: 5733154 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4802. Min Act: -0.1700

Data Index: 5163767 (Open Web Text)

Max Activating Token Index: 690

Text #19

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4700. Min Act: -0.1700

Data Index: 1979706 (Open Web Text)

Max Activating Token Index: 117