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

Dataset: Open Web Text

Neuron 416 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: 4.8933. Min Range: -4.8933

Max Act: 4.8933. Min Act: -0.1700

Data Index: 4436249 (Open Web Text)

Max Activating Token Index: 792

Text #1

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.7078. Min Act: -0.1700

Data Index: 2384889 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6884. Min Act: -0.1700

Data Index: 5744302 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6797. Min Act: -0.1700

Data Index: 7603734 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6156. Min Act: -0.1700

Data Index: 747220 (Open Web Text)

Max Activating Token Index: 835

Text #5

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6459. Min Act: -0.1700

Data Index: 3052892 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6276. Min Act: -0.1700

Data Index: 3170317 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6405. Min Act: -0.1700

Data Index: 4335855 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6148. Min Act: -0.1700

Data Index: 2973497 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.6246. Min Act: -0.1700

Data Index: 3140625 (Open Web Text)

Max Activating Token Index: 872

Text #10

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5957. Min Act: -0.1700

Data Index: 7137011 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5964. Min Act: -0.1700

Data Index: 5948183 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5659. Min Act: -0.1700

Data Index: 532563 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5363. Min Act: -0.1700

Data Index: 1450449 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5676. Min Act: -0.1700

Data Index: 389453 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5584. Min Act: -0.1700

Data Index: 2211698 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5553. Min Act: -0.1700

Data Index: 3951390 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5259. Min Act: -0.1700

Data Index: 6760334 (Open Web Text)

Max Activating Token Index: 619

Text #18

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5414. Min Act: -0.1700

Data Index: 3644229 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.8933. Min Range: -4.8933

Max Act: 4.5442. Min Act: -0.1700

Data Index: 5220562 (Open Web Text)

Max Activating Token Index: 691