Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 528 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.3894. Min Act: -0.1700
Data Index: 2246819 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.3269. Min Act: -0.1700
Data Index: 8480858 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.2331. Min Act: -0.1700
Data Index: 5111577 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.2331. Min Act: -0.1700
Data Index: 1964153 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.1706. Min Act: -0.1700
Data Index: 691419 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.1081. Min Act: -0.1700
Data Index: 39178 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.1081. Min Act: -0.1700
Data Index: 3116598 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.1081. Min Act: -0.1700
Data Index: 8041285 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0769. Min Act: -0.1700
Data Index: 3496277 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0769. Min Act: -0.1700
Data Index: 647797 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0769. Min Act: -0.1700
Data Index: 8231523 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0769. Min Act: -0.1700
Data Index: 7782866 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0769. Min Act: -0.1700
Data Index: 2302470 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0456. Min Act: -0.1700
Data Index: 6969911 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0456. Min Act: -0.1700
Data Index: 901751 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0769. Min Act: -0.1700
Data Index: 4539607 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0456. Min Act: -0.1700
Data Index: 776445 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0144. Min Act: -0.1700
Data Index: 5277122 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0456. Min Act: -0.1700
Data Index: 5668266 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3894. Min Range: -5.3894
Max Act: 5.0144. Min Act: -0.1700
Data Index: 723989 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19