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

Dataset: Open Web Text

Neuron 170 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: 4.8696. Min Range: -4.8696

Max Act: 4.8696. Min Act: -0.1700

Data Index: 8463719 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.8140. Min Act: -0.1700

Data Index: 1600467 (Open Web Text)

Max Activating Token Index: 1008

Text #2

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.8227. Min Act: -0.1700

Data Index: 8350615 (Open Web Text)

Max Activating Token Index: 165

Text #3

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7824. Min Act: -0.1700

Data Index: 3357839 (Open Web Text)

Max Activating Token Index: 992

Text #4

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7526. Min Act: -0.1700

Data Index: 5325214 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7679. Min Act: -0.1700

Data Index: 5857070 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7504. Min Act: -0.1700

Data Index: 4917829 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7742. Min Act: -0.1700

Data Index: 7060030 (Open Web Text)

Max Activating Token Index: 213

Text #8

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7446. Min Act: -0.1700

Data Index: 8461473 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7604. Min Act: -0.1700

Data Index: 4531546 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7227. Min Act: -0.1700

Data Index: 1170820 (Open Web Text)

Max Activating Token Index: 848

Text #11

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7242. Min Act: -0.1700

Data Index: 286373 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7122. Min Act: -0.1700

Data Index: 851882 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7024. Min Act: -0.1700

Data Index: 2357180 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.6988. Min Act: -0.1700

Data Index: 4958831 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.6948. Min Act: -0.1700

Data Index: 7924005 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.6576. Min Act: -0.1700

Data Index: 5291375 (Open Web Text)

Max Activating Token Index: 994

Text #17

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.6691. Min Act: -0.1700

Data Index: 2817053 (Open Web Text)

Max Activating Token Index: 878

Text #18

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.6387. Min Act: -0.1700

Data Index: 7543609 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.6168. Min Act: -0.1700

Data Index: 6350064 (Open Web Text)

Max Activating Token Index: 22