Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7095. Min Range: -7.7095
Max Act: 7.7095. Min Act: -0.1700
Data Index: 5242216 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7095. Min Range: -7.7095
Max Act: 7.6470. Min Act: -0.1700
Data Index: 3188666 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7095. Min Range: -7.7095
Max Act: 7.3345. Min Act: -0.1700
Data Index: 436041 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.9907. Min Act: -0.1700
Data Index: 2880346 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.9907. Min Act: -0.1700
Data Index: 6213672 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.9907. Min Act: -0.1700
Data Index: 7497970 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.9595. Min Act: -0.1700
Data Index: 5804645 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.9282. Min Act: -0.1700
Data Index: 5374920 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.9282. Min Act: -0.1700
Data Index: 7282093 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8657. Min Act: -0.1700
Data Index: 3731014 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8657. Min Act: -0.1700
Data Index: 2782130 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8657. Min Act: -0.1700
Data Index: 8347979 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8345. Min Act: -0.1700
Data Index: 3703970 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8345. Min Act: -0.1700
Data Index: 3773887 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8345. Min Act: -0.1700
Data Index: 4848601 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.8032. Min Act: -0.1700
Data Index: 8802356 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 7749879 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.7407. Min Act: -0.1700
Data Index: 3503803 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 2478318 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7095. Min Range: -7.7095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 8035027 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19