Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1888 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.8403. Min Act: -0.1700
Data Index: 2000527 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.8403. Min Act: -0.1700
Data Index: 2289585 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.8091. Min Act: -0.1700
Data Index: 8236434 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.7466. Min Act: -0.1700
Data Index: 6272460 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.7153. Min Act: -0.1700
Data Index: 4920382 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.7153. Min Act: -0.1700
Data Index: 8545083 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.7153. Min Act: -0.1700
Data Index: 1397582 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.7466. Min Act: -0.1700
Data Index: 992126 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6841. Min Act: -0.1700
Data Index: 460150 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 6844171 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 1300002 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 6213428 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 5945901 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6216. Min Act: -0.1700
Data Index: 8762494 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6216. Min Act: -0.1700
Data Index: 4451188 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.6216. Min Act: -0.1700
Data Index: 3478651 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.5903. Min Act: -0.1700
Data Index: 6744203 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.5591. Min Act: -0.1700
Data Index: 8283917 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.5903. Min Act: -0.1700
Data Index: 3621122 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8403. Min Range: -7.8403
Max Act: 7.5591. Min Act: -0.1700
Data Index: 5198904 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19