Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.7504. Min Act: -0.1700
Data Index: 263851 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.7192. Min Act: -0.1700
Data Index: 3301148 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.7192. Min Act: -0.1700
Data Index: 7965597 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.6879. Min Act: -0.1700
Data Index: 6231278 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.5004. Min Act: -0.1700
Data Index: 1947732 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.2504. Min Act: -0.1700
Data Index: 8242077 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.1567. Min Act: -0.1700
Data Index: 6148417 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.0942. Min Act: -0.1700
Data Index: 8220895 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7504. Min Range: -7.7504
Max Act: 7.0317. Min Act: -0.1700
Data Index: 7675368 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 2277633 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 7185467 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 893755 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8754. Min Act: -0.1700
Data Index: 6690302 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8754. Min Act: -0.1700
Data Index: 36605 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8442. Min Act: -0.1700
Data Index: 8652271 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8442. Min Act: -0.1700
Data Index: 1739375 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8129. Min Act: -0.1700
Data Index: 3376282 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8129. Min Act: -0.1700
Data Index: 1305080 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8129. Min Act: -0.1700
Data Index: 7029056 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7504. Min Range: -7.7504
Max Act: 6.8442. Min Act: -0.1700
Data Index: 5249180 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19