Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5887 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1697. Min Range: -9.1697
Max Act: 9.1697. Min Act: -0.1700
Data Index: 6416011 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1697. Min Range: -9.1697
Max Act: 9.0447. Min Act: -0.1700
Data Index: 2129429 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.9197. Min Act: -0.1700
Data Index: 633079 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.8572. Min Act: -0.1700
Data Index: 4982369 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.7947. Min Act: -0.1700
Data Index: 6014268 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.7947. Min Act: -0.1700
Data Index: 8678569 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.7947. Min Act: -0.1700
Data Index: 914444 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.7322. Min Act: -0.1700
Data Index: 6002454 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.7322. Min Act: -0.1700
Data Index: 4875217 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.6072. Min Act: -0.1700
Data Index: 140292 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.6072. Min Act: -0.1700
Data Index: 769227 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.6072. Min Act: -0.1700
Data Index: 20573 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.6072. Min Act: -0.1700
Data Index: 179947 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.6072. Min Act: -0.1700
Data Index: 1424991 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.6072. Min Act: -0.1700
Data Index: 193174 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.5447. Min Act: -0.1700
Data Index: 7515613 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.5447. Min Act: -0.1700
Data Index: 8639959 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.5447. Min Act: -0.1700
Data Index: 3834889 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.5447. Min Act: -0.1700
Data Index: 185820 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1697. Min Range: -9.1697
Max Act: 8.5447. Min Act: -0.1700
Data Index: 4659409 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19