Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5921 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.5725. Min Act: -0.1700
Data Index: 761334 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.5413. Min Act: -0.1700
Data Index: 99284 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.4475. Min Act: -0.1700
Data Index: 8672674 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.2288. Min Act: -0.1700
Data Index: 7014436 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.2600. Min Act: -0.1700
Data Index: 3457305 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.1663. Min Act: -0.1700
Data Index: 3629236 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.1038. Min Act: -0.1700
Data Index: 908079 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.1038. Min Act: -0.1700
Data Index: 1650223 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.1350. Min Act: -0.1700
Data Index: 7422192 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.0725. Min Act: -0.1700
Data Index: 247092 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3004147 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5725. Min Range: -6.5725
Max Act: 6.0100. Min Act: -0.1700
Data Index: 5001822 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9788. Min Act: -0.1700
Data Index: 4663895 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9788. Min Act: -0.1700
Data Index: 3967780 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9788. Min Act: -0.1700
Data Index: 7676517 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9475. Min Act: -0.1700
Data Index: 1035535 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9475. Min Act: -0.1700
Data Index: 1223275 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.8850. Min Act: -0.1700
Data Index: 4410235 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9163. Min Act: -0.1698
Data Index: 619380 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5725. Min Range: -6.5725
Max Act: 5.9163. Min Act: -0.1700
Data Index: 154789 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19