Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0249. Min Range: -8.0249
Max Act: 8.0249. Min Act: -0.1700
Data Index: 7037306 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0249. Min Range: -8.0249
Max Act: 7.3687. Min Act: -0.1700
Data Index: 7927315 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.9937. Min Act: -0.1700
Data Index: 8165149 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 8520442 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.8999. Min Act: -0.1700
Data Index: 806713 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.8374. Min Act: -0.1700
Data Index: 8196929 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.7437. Min Act: -0.1700
Data Index: 575428 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.7437. Min Act: -0.1700
Data Index: 276591 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.7124. Min Act: -0.1700
Data Index: 4766271 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6812. Min Act: -0.1700
Data Index: 6019685 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.7124. Min Act: -0.1700
Data Index: 469923 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6812. Min Act: -0.1700
Data Index: 1715640 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6812. Min Act: -0.1700
Data Index: 1715641 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6187. Min Act: -0.1700
Data Index: 8089607 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6187. Min Act: -0.1700
Data Index: 2515438 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6187. Min Act: -0.1700
Data Index: 1971140 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.5874. Min Act: -0.1700
Data Index: 2240 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.5874. Min Act: -0.1700
Data Index: 7273166 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6187. Min Act: -0.1700
Data Index: 995249 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0249. Min Range: -8.0249
Max Act: 6.6187. Min Act: -0.1700
Data Index: 2949322 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19