Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0472. Min Range: -5.0472
Max Act: 5.0472. Min Act: -0.1700
Data Index: 3384926 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.9222. Min Act: -0.1700
Data Index: 6073029 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8909. Min Act: -0.1700
Data Index: 1790393 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3314338 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3314334 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8284. Min Act: -0.1700
Data Index: 6135789 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8284. Min Act: -0.1700
Data Index: 7753028 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8284. Min Act: -0.1700
Data Index: 5846806 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.8284. Min Act: -0.1700
Data Index: 5644995 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7972. Min Act: -0.1700
Data Index: 3314345 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7972. Min Act: -0.1700
Data Index: 5870587 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7972. Min Act: -0.1700
Data Index: 3314349 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7972. Min Act: -0.1700
Data Index: 2259458 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7972. Min Act: -0.1700
Data Index: 3314333 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7972. Min Act: -0.1700
Data Index: 3314335 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7659. Min Act: -0.1700
Data Index: 348977 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7659. Min Act: -0.1700
Data Index: 4017684 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7659. Min Act: -0.1700
Data Index: 3314352 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7347. Min Act: -0.1700
Data Index: 3314328 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0472. Min Range: -5.0472
Max Act: 4.7347. Min Act: -0.1700
Data Index: 4454602 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19