Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1910 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.9928. Min Act: -0.1700
Data Index: 421588 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.8053. Min Act: -0.1700
Data Index: 5798402 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.7115. Min Act: -0.1700
Data Index: 782954 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.7115. Min Act: -0.1700
Data Index: 3620292 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6803. Min Act: -0.1700
Data Index: 8280649 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 7775738 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6490. Min Act: -0.1700
Data Index: 3424918 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6178. Min Act: -0.1700
Data Index: 2231373 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.6178. Min Act: -0.1700
Data Index: 8166935 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5865. Min Act: -0.1700
Data Index: 6618394 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5553. Min Act: -0.1700
Data Index: 260169 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5553. Min Act: -0.1700
Data Index: 3770372 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5553. Min Act: -0.1700
Data Index: 129147 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5553. Min Act: -0.1700
Data Index: 8141156 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5553. Min Act: -0.1700
Data Index: 368139 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5553. Min Act: -0.1700
Data Index: 8568852 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5240. Min Act: -0.1700
Data Index: 7811683 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5240. Min Act: -0.1700
Data Index: 4767729 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.5240. Min Act: -0.1700
Data Index: 8585038 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9928. Min Range: -6.9928
Max Act: 6.4928. Min Act: -0.1700
Data Index: 825265 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19