Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2894. Min Range: -6.2894
Max Act: 6.2894. Min Act: -0.1700
Data Index: 3015815 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2894. Min Range: -6.2894
Max Act: 6.1957. Min Act: -0.1700
Data Index: 3968179 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2894. Min Range: -6.2894
Max Act: 6.0082. Min Act: -0.1700
Data Index: 7458573 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.9769. Min Act: -0.1700
Data Index: 1726716 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.9457. Min Act: -0.1700
Data Index: 3108757 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4924183 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.8207. Min Act: -0.1700
Data Index: 3443675 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7894. Min Act: -0.1700
Data Index: 2686723 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7894. Min Act: -0.1700
Data Index: 1585864 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7894. Min Act: -0.1700
Data Index: 2562737 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7894. Min Act: -0.1700
Data Index: 7063217 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7894. Min Act: -0.1700
Data Index: 1619928 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7582. Min Act: -0.1700
Data Index: 6119712 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7582. Min Act: -0.1700
Data Index: 380569 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7582. Min Act: -0.1700
Data Index: 7328848 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7582. Min Act: -0.1700
Data Index: 1631173 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7582. Min Act: -0.1700
Data Index: 1755057 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7269. Min Act: -0.1700
Data Index: 3455144 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.7269. Min Act: -0.1700
Data Index: 1872540 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2894. Min Range: -6.2894
Max Act: 5.6957. Min Act: -0.1700
Data Index: 2999808 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19