Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5644. Min Range: -9.5644
Max Act: 9.5644. Min Act: -0.1700
Data Index: 4171749 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.8144. Min Act: -0.1700
Data Index: 7632979 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.8769. Min Act: -0.1700
Data Index: 705159 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.5644. Min Act: -0.1700
Data Index: 8019354 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.5019. Min Act: -0.1700
Data Index: 5300994 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.4394. Min Act: -0.1700
Data Index: 3248750 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.3769. Min Act: -0.1700
Data Index: 8030662 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.3769. Min Act: -0.1700
Data Index: 8654751 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.3769. Min Act: -0.1700
Data Index: 171374 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.3769. Min Act: -0.1700
Data Index: 1795154 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.2519. Min Act: -0.1700
Data Index: 6688460 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.2519. Min Act: -0.1700
Data Index: 3880751 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1894. Min Act: -0.1700
Data Index: 7056664 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1894. Min Act: -0.1700
Data Index: 4552861 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1894. Min Act: -0.1700
Data Index: 361796 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1269. Min Act: -0.1700
Data Index: 1399961 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1894. Min Act: -0.1700
Data Index: 7837094 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1894. Min Act: -0.1700
Data Index: 6626475 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1269. Min Act: -0.1700
Data Index: 98072 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5644. Min Range: -9.5644
Max Act: 8.1269. Min Act: -0.1700
Data Index: 5372773 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19