Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5384 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.7004. Min Act: -0.1700
Data Index: 1754556 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.6691. Min Act: -0.1700
Data Index: 1917636 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.5908. Min Act: -0.1700
Data Index: 428332 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4655. Min Act: -0.1700
Data Index: 8139571 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4812. Min Act: -0.1700
Data Index: 8357523 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4969. Min Act: -0.1700
Data Index: 2928960 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4812. Min Act: -0.1700
Data Index: 1015168 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4499. Min Act: -0.1700
Data Index: 6076960 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4185. Min Act: -0.1700
Data Index: 3581254 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4185. Min Act: -0.1700
Data Index: 8362877 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4342. Min Act: -0.1700
Data Index: 8713067 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.4342. Min Act: -0.1700
Data Index: 4400187 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3872. Min Act: -0.1700
Data Index: 745691 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3715. Min Act: -0.1700
Data Index: 6155895 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3558. Min Act: -0.1700
Data Index: 3386594 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3558. Min Act: -0.1700
Data Index: 7829331 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3558. Min Act: -0.1700
Data Index: 8788151 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3244. Min Act: -0.1700
Data Index: 7358757 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3244. Min Act: -0.1700
Data Index: 8240314 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7004. Min Range: -3.7004
Max Act: 3.3087. Min Act: -0.1700
Data Index: 116186 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19