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

Dataset: Open Web Text

Neuron 244 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: 4.8914. Min Range: -4.8914

Max Act: 4.8914. Min Act: -0.1700

Data Index: 6791880 (Open Web Text)

Max Activating Token Index: 596

Text #1

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.8439. Min Act: -0.1700

Data Index: 4927608 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7444. Min Act: -0.1700

Data Index: 5617367 (Open Web Text)

Max Activating Token Index: 752

Text #3

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7378. Min Act: -0.1700

Data Index: 5034556 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7324. Min Act: -0.1700

Data Index: 5246801 (Open Web Text)

Max Activating Token Index: 284

Text #5

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7369. Min Act: -0.1700

Data Index: 4385482 (Open Web Text)

Max Activating Token Index: 755

Text #6

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7303. Min Act: -0.1700

Data Index: 2700290 (Open Web Text)

Max Activating Token Index: 366

Text #7

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6772. Min Act: -0.1700

Data Index: 3737306 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7030. Min Act: -0.1700

Data Index: 8431622 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6598. Min Act: -0.1700

Data Index: 1146595 (Open Web Text)

Max Activating Token Index: 913

Text #10

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6902. Min Act: -0.1700

Data Index: 8027381 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6823. Min Act: -0.1700

Data Index: 899208 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.7090. Min Act: -0.1700

Data Index: 7283700 (Open Web Text)

Max Activating Token Index: 450

Text #13

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6585. Min Act: -0.1700

Data Index: 3720103 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6695. Min Act: -0.1700

Data Index: 3395025 (Open Web Text)

Max Activating Token Index: 773

Text #15

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6635. Min Act: -0.1700

Data Index: 5211202 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6598. Min Act: -0.1700

Data Index: 1700167 (Open Web Text)

Max Activating Token Index: 935

Text #17

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6845. Min Act: -0.1700

Data Index: 5283942 (Open Web Text)

Max Activating Token Index: 188

Text #18

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6754. Min Act: -0.1700

Data Index: 5858753 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 4.8914. Min Range: -4.8914

Max Act: 4.6405. Min Act: -0.1700

Data Index: 6048763 (Open Web Text)

Max Activating Token Index: 149