Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1291 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7783. Min Act: -0.1700
Data Index: 4803982 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7158. Min Act: -0.1700
Data Index: 5557139 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.6221. Min Act: -0.1700
Data Index: 3347217 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.6533. Min Act: -0.1700
Data Index: 4381002 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.5908. Min Act: -0.1700
Data Index: 4522435 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.5283. Min Act: -0.1700
Data Index: 325310 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.5283. Min Act: -0.1700
Data Index: 6543631 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4658. Min Act: -0.1700
Data Index: 6634667 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4346. Min Act: -0.1700
Data Index: 2502713 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4346. Min Act: -0.1700
Data Index: 6076719 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4658. Min Act: -0.1700
Data Index: 1039905 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4346. Min Act: -0.1700
Data Index: 6409608 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4033. Min Act: -0.1700
Data Index: 6466829 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4033. Min Act: -0.1700
Data Index: 6894583 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4346. Min Act: -0.1700
Data Index: 5198843 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3721. Min Act: -0.1700
Data Index: 4135418 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3408. Min Act: -0.1700
Data Index: 468569 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3096. Min Act: -0.1700
Data Index: 3573457 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3408. Min Act: -0.1700
Data Index: 575348 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3096. Min Act: -0.1700
Data Index: 2754817 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19