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

Dataset: Open Web Text

Neuron 185 in Layer 5

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: 6.2581. Min Range: -6.2581

Max Act: 6.1906. Min Act: -0.1700

Data Index: 8180834 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.2581. Min Act: -0.1700

Data Index: 5518015 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.1360. Min Act: -0.1700

Data Index: 2659047 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.1499. Min Act: -0.1700

Data Index: 7741467 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.1260. Min Act: -0.1700

Data Index: 6110381 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.0536. Min Act: -0.1700

Data Index: 2673132 (Open Web Text)

Max Activating Token Index: 504

Text #6

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.0405. Min Act: -0.1700

Data Index: 7150739 (Open Web Text)

Max Activating Token Index: 889

Text #7

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.0897. Min Act: -0.1700

Data Index: 3107540 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.9735. Min Act: -0.1700

Data Index: 696745 (Open Web Text)

Max Activating Token Index: 788

Text #9

Max Range: 6.2581. Min Range: -6.2581

Max Act: 6.0005. Min Act: -0.1700

Data Index: 3280982 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.9403. Min Act: -0.1700

Data Index: 3614440 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.9012. Min Act: -0.1700

Data Index: 8586673 (Open Web Text)

Max Activating Token Index: 736

Text #12

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.8304. Min Act: -0.1700

Data Index: 7741468 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.7857. Min Act: -0.1700

Data Index: 4459216 (Open Web Text)

Max Activating Token Index: 678

Text #14

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.7518. Min Act: -0.1700

Data Index: 7421718 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.7855. Min Act: -0.1700

Data Index: 8785653 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.5687. Min Act: -0.1700

Data Index: 7010895 (Open Web Text)

Max Activating Token Index: 1014

Text #17

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.7123. Min Act: -0.1700

Data Index: 5215068 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.7133. Min Act: -0.1700

Data Index: 1356898 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 6.2581. Min Range: -6.2581

Max Act: 5.6507. Min Act: -0.1700

Data Index: 3107541 (Open Web Text)

Max Activating Token Index: 777