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

Dataset: Open Web Text

Neuron 932 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: 3.6945. Min Range: -3.6945

Max Act: 3.6945. Min Act: -0.1700

Data Index: 5075903 (Open Web Text)

Max Activating Token Index: 807

Text #1

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6763. Min Act: -0.1700

Data Index: 7154242 (Open Web Text)

Max Activating Token Index: 790

Text #2

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6405. Min Act: -0.1700

Data Index: 5763331 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6351. Min Act: -0.1700

Data Index: 568236 (Open Web Text)

Max Activating Token Index: 204

Text #4

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6710. Min Act: -0.1700

Data Index: 8613808 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6238. Min Act: -0.1700

Data Index: 648455 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6003. Min Act: -0.1700

Data Index: 42916 (Open Web Text)

Max Activating Token Index: 886

Text #7

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6202. Min Act: -0.1700

Data Index: 4466666 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5925. Min Act: -0.1700

Data Index: 8597086 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5936. Min Act: -0.1700

Data Index: 4798860 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5929. Min Act: -0.1700

Data Index: 6262068 (Open Web Text)

Max Activating Token Index: 545

Text #11

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5961. Min Act: -0.1700

Data Index: 6855626 (Open Web Text)

Max Activating Token Index: 823

Text #12

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5878. Min Act: -0.1700

Data Index: 8810059 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.6029. Min Act: -0.1700

Data Index: 1104058 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5616. Min Act: -0.1700

Data Index: 1358762 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5360. Min Act: -0.1700

Data Index: 3426148 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5466. Min Act: -0.1700

Data Index: 2521660 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5708. Min Act: -0.1700

Data Index: 287267 (Open Web Text)

Max Activating Token Index: 836

Text #18

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5590. Min Act: -0.1700

Data Index: 1071562 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 3.6945. Min Range: -3.6945

Max Act: 3.5566. Min Act: -0.1700

Data Index: 5186189 (Open Web Text)

Max Activating Token Index: 1009