Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.5450. Min Act: -0.1700
Data Index: 1748811 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.5450. Min Act: -0.1700
Data Index: 1769273 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.5450. Min Act: -0.1700
Data Index: 3872852 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.3575. Min Act: -0.1700
Data Index: 6776633 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.3575. Min Act: -0.1700
Data Index: 6889836 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.2325. Min Act: -0.1700
Data Index: 6282556 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.2325. Min Act: -0.1700
Data Index: 1009929 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.1700. Min Act: -0.1700
Data Index: 4605374 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.2325. Min Act: -0.1700
Data Index: 5628528 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.1387. Min Act: -0.1700
Data Index: 8809560 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.1075. Min Act: -0.1700
Data Index: 6324584 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.0450. Min Act: -0.1700
Data Index: 3639311 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.0450. Min Act: -0.1700
Data Index: 8395375 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.0450. Min Act: -0.1700
Data Index: 7597082 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5450. Min Range: -8.5450
Max Act: 7.9825. Min Act: -0.1700
Data Index: 7375667 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5450. Min Range: -8.5450
Max Act: 8.0137. Min Act: -0.1700
Data Index: 3052911 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5450. Min Range: -8.5450
Max Act: 7.9825. Min Act: -0.1700
Data Index: 6135823 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5450. Min Range: -8.5450
Max Act: 7.9200. Min Act: -0.1700
Data Index: 445021 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5450. Min Range: -8.5450
Max Act: 7.8887. Min Act: -0.1700
Data Index: 6740404 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5450. Min Range: -8.5450
Max Act: 7.9200. Min Act: -0.1700
Data Index: 3338 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19