Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.9115. Min Act: -0.1700
Data Index: 923227 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.8490. Min Act: -0.1700
Data Index: 8400984 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.8490. Min Act: -0.1700
Data Index: 6504366 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.8178. Min Act: -0.1700
Data Index: 923241 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7865. Min Act: -0.1700
Data Index: 1212510 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7553. Min Act: -0.1700
Data Index: 89800 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7240. Min Act: -0.1700
Data Index: 2639748 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7553. Min Act: -0.1700
Data Index: 923239 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7553. Min Act: -0.1700
Data Index: 6666655 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7240. Min Act: -0.1700
Data Index: 8162521 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.7240. Min Act: -0.1700
Data Index: 629619 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6928. Min Act: -0.1700
Data Index: 2970318 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6928. Min Act: -0.1700
Data Index: 2970316 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6928. Min Act: -0.1700
Data Index: 8525035 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6615. Min Act: -0.1700
Data Index: 5669075 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6303. Min Act: -0.1700
Data Index: 8021104 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6615. Min Act: -0.1700
Data Index: 6254735 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6615. Min Act: -0.1700
Data Index: 404245 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6615. Min Act: -0.1700
Data Index: 8484964 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9115. Min Range: -4.9115
Max Act: 4.6303. Min Act: -0.1700
Data Index: 8400982 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19