Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3428. Min Range: -6.3428
Max Act: 6.3428. Min Act: -0.1700
Data Index: 147339 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3428. Min Range: -6.3428
Max Act: 6.2178. Min Act: -0.1700
Data Index: 5468282 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3428. Min Range: -6.3428
Max Act: 6.1553. Min Act: -0.1700
Data Index: 8128606 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3428. Min Range: -6.3428
Max Act: 6.0928. Min Act: -0.1700
Data Index: 6709608 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.9678. Min Act: -0.1700
Data Index: 3998517 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.9366. Min Act: -0.1700
Data Index: 8447493 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.9366. Min Act: -0.1700
Data Index: 3323995 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.9053. Min Act: -0.1700
Data Index: 2784758 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.8741. Min Act: -0.1700
Data Index: 1574905 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.8116. Min Act: -0.1700
Data Index: 2477212 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.8428. Min Act: -0.1700
Data Index: 7145356 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.8116. Min Act: -0.1700
Data Index: 2640539 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.7178. Min Act: -0.1700
Data Index: 7762543 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.7178. Min Act: -0.1700
Data Index: 2860128 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.7178. Min Act: -0.1700
Data Index: 5826226 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.7178. Min Act: -0.1700
Data Index: 6853337 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.7178. Min Act: -0.1700
Data Index: 7134008 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.6553. Min Act: -0.1700
Data Index: 3135892 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.6866. Min Act: -0.1700
Data Index: 836833 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3428. Min Range: -6.3428
Max Act: 5.6553. Min Act: -0.1700
Data Index: 3687896 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19