Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4856 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.1178. Min Act: -0.1700
Data Index: 6031609 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3927596 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.1178. Min Act: -0.1700
Data Index: 6695462 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0865. Min Act: -0.1700
Data Index: 1526440 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0553. Min Act: -0.1700
Data Index: 2862713 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0553. Min Act: -0.1700
Data Index: 7515440 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0553. Min Act: -0.1700
Data Index: 7926404 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0553. Min Act: -0.1700
Data Index: 1979269 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0240. Min Act: -0.1700
Data Index: 1512991 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4433937 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0240. Min Act: -0.1699
Data Index: 4442980 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1178. Min Range: -5.1178
Max Act: 5.0240. Min Act: -0.1700
Data Index: 7986023 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9928. Min Act: -0.1700
Data Index: 2161245 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9615. Min Act: -0.1700
Data Index: 5782321 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9928. Min Act: -0.1700
Data Index: 6199348 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9615. Min Act: -0.1699
Data Index: 7004008 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4606749 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9615. Min Act: -0.1700
Data Index: 6548376 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9615. Min Act: -0.1700
Data Index: 5430066 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1178. Min Range: -5.1178
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4006433 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19