Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.6244. Min Act: -0.1700
Data Index: 353292 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.4369. Min Act: -0.1700
Data Index: 2091483 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.4369. Min Act: -0.1700
Data Index: 8285011 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.4056. Min Act: -0.1700
Data Index: 3544289 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.3744. Min Act: -0.1700
Data Index: 4031202 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.3744. Min Act: -0.1700
Data Index: 7711797 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2806. Min Act: -0.1700
Data Index: 1927117 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2806. Min Act: -0.1700
Data Index: 5430164 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2494. Min Act: -0.1700
Data Index: 7337027 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2494. Min Act: -0.1700
Data Index: 4655139 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2494. Min Act: -0.1700
Data Index: 1984262 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2181. Min Act: -0.1700
Data Index: 6088392 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2181. Min Act: -0.1700
Data Index: 3420696 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.2181. Min Act: -0.1700
Data Index: 5409914 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.1869. Min Act: -0.1700
Data Index: 5692553 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.1869. Min Act: -0.1700
Data Index: 5157905 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.1556. Min Act: -0.1700
Data Index: 677656 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.1244. Min Act: -0.1700
Data Index: 5602642 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.1244. Min Act: -0.1700
Data Index: 892251 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6244. Min Range: -5.6244
Max Act: 5.1244. Min Act: -0.1700
Data Index: 3529830 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19