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

Dataset: Open Web Text

Neuron 83 in Layer 6

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: 3.0023. Min Range: -3.0023

Max Act: 3.0023. Min Act: -0.1700

Data Index: 2753966 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.9662. Min Act: -0.1700

Data Index: 6107878 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.9638. Min Act: -0.1700

Data Index: 7350819 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.9491. Min Act: -0.1700

Data Index: 3836742 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.9410. Min Act: -0.1700

Data Index: 356794 (Open Web Text)

Max Activating Token Index: 727

Text #5

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.9091. Min Act: -0.1700

Data Index: 6245466 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8473. Min Act: -0.1700

Data Index: 290937 (Open Web Text)

Max Activating Token Index: 902

Text #7

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8759. Min Act: -0.1700

Data Index: 3681565 (Open Web Text)

Max Activating Token Index: 861

Text #8

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8518. Min Act: -0.1700

Data Index: 4746053 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8503. Min Act: -0.1700

Data Index: 8706210 (Open Web Text)

Max Activating Token Index: 568

Text #10

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8519. Min Act: -0.1700

Data Index: 3354761 (Open Web Text)

Max Activating Token Index: 957

Text #11

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8151. Min Act: -0.1700

Data Index: 3916399 (Open Web Text)

Max Activating Token Index: 885

Text #12

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8231. Min Act: -0.1700

Data Index: 7467098 (Open Web Text)

Max Activating Token Index: 92

Text #13

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8205. Min Act: -0.1700

Data Index: 8217842 (Open Web Text)

Max Activating Token Index: 677

Text #14

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8217. Min Act: -0.1700

Data Index: 6140740 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8041. Min Act: -0.1700

Data Index: 3814667 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.7936. Min Act: -0.1700

Data Index: 5958534 (Open Web Text)

Max Activating Token Index: 890

Text #17

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.7960. Min Act: -0.1700

Data Index: 4174290 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.8016. Min Act: -0.1700

Data Index: 8521181 (Open Web Text)

Max Activating Token Index: 56

Text #19

Max Range: 3.0023. Min Range: -3.0023

Max Act: 2.7956. Min Act: -0.1700

Data Index: 4872838 (Open Web Text)

Max Activating Token Index: 366