Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 875 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1282. Min Range: -5.1282
Max Act: 5.1282. Min Act: -0.1700
Data Index: 7568147 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1282. Min Range: -5.1282
Max Act: 5.0032. Min Act: -0.1700
Data Index: 90240 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1282. Min Range: -5.1282
Max Act: 5.0345. Min Act: -0.1700
Data Index: 7802199 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1282. Min Range: -5.1282
Max Act: 5.0032. Min Act: -0.1700
Data Index: 8042668 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1282. Min Range: -5.1282
Max Act: 5.0032. Min Act: -0.1700
Data Index: 3791624 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.9095. Min Act: -0.1700
Data Index: 1358791 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.8782. Min Act: -0.1700
Data Index: 4602684 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.8157. Min Act: -0.1700
Data Index: 1328610 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.8470. Min Act: -0.1700
Data Index: 4088180 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.7845. Min Act: -0.1700
Data Index: 2235112 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.7532. Min Act: -0.1700
Data Index: 2834454 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.7532. Min Act: -0.1700
Data Index: 1343258 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.7220. Min Act: -0.1700
Data Index: 4856670 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6907. Min Act: -0.1700
Data Index: 3380013 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6907. Min Act: -0.1700
Data Index: 7661927 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6907. Min Act: -0.1700
Data Index: 6464071 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6907. Min Act: -0.1700
Data Index: 6308622 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6907. Min Act: -0.1700
Data Index: 4428501 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6595. Min Act: -0.1700
Data Index: 5200160 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1282. Min Range: -5.1282
Max Act: 4.6907. Min Act: -0.1700
Data Index: 2020150 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19