Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3519. Min Range: -8.3519
Max Act: 8.3519. Min Act: -0.1700
Data Index: 6596561 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3519. Min Range: -8.3519
Max Act: 8.0082. Min Act: -0.1700
Data Index: 2584726 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.8832. Min Act: -0.1700
Data Index: 3752098 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.8832. Min Act: -0.1700
Data Index: 2584729 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.7894. Min Act: -0.1700
Data Index: 2979299 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.7582. Min Act: -0.1700
Data Index: 2386185 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.6957. Min Act: -0.1700
Data Index: 2836657 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.7269. Min Act: -0.1700
Data Index: 80991 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.4769. Min Act: -0.1700
Data Index: 232297 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.4457. Min Act: -0.1700
Data Index: 1970910 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.3832. Min Act: -0.1700
Data Index: 6844404 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.3832. Min Act: -0.1700
Data Index: 2948099 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.3519. Min Act: -0.1700
Data Index: 2936409 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2894. Min Act: -0.1700
Data Index: 1513764 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2582. Min Act: -0.1700
Data Index: 4735414 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2582. Min Act: -0.1700
Data Index: 5909613 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2582. Min Act: -0.1700
Data Index: 1365059 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2269. Min Act: -0.1700
Data Index: 4642891 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2269. Min Act: -0.1700
Data Index: 2584727 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3519. Min Range: -8.3519
Max Act: 7.2269. Min Act: -0.1700
Data Index: 1022726 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19