Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.4688. Min Act: -0.1700
Data Index: 3991328 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.1563. Min Act: -0.1700
Data Index: 1295181 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.1250. Min Act: -0.1700
Data Index: 833818 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.1250. Min Act: -0.1700
Data Index: 4199508 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.0938. Min Act: -0.1700
Data Index: 171882 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.0938. Min Act: -0.1700
Data Index: 2229673 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4688. Min Range: -5.4688
Max Act: 5.0000. Min Act: -0.1700
Data Index: 5019228 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9688. Min Act: -0.1700
Data Index: 8818896 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 7817828 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9688. Min Act: -0.1700
Data Index: 7469982 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 2759544 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 7660133 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 7643143 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 451791 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 2974231 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9375. Min Act: -0.1700
Data Index: 2490663 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9063. Min Act: -0.1700
Data Index: 7310129 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.9063. Min Act: -0.1700
Data Index: 8430755 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.8750. Min Act: -0.1700
Data Index: 7985435 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4688. Min Range: -5.4688
Max Act: 4.8750. Min Act: -0.1700
Data Index: 7192483 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19