Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6291 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.7871. Min Act: -0.1700
Data Index: 2684309 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.7246. Min Act: -0.1700
Data Index: 4723381 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.7246. Min Act: -0.1700
Data Index: 7426846 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.6934. Min Act: -0.1700
Data Index: 8178769 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.6934. Min Act: -0.1700
Data Index: 6371651 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.6934. Min Act: -0.1700
Data Index: 59888 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.6621. Min Act: -0.1700
Data Index: 7117713 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.6309. Min Act: -0.1700
Data Index: 5331459 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.6309. Min Act: -0.1700
Data Index: 5996644 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5996. Min Act: -0.1700
Data Index: 468960 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5684. Min Act: -0.1700
Data Index: 3390939 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5684. Min Act: -0.1700
Data Index: 3687913 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5684. Min Act: -0.1700
Data Index: 5529090 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5684. Min Act: -0.1700
Data Index: 7528562 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5371. Min Act: -0.1700
Data Index: 4224601 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5371. Min Act: -0.1700
Data Index: 3831372 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5059. Min Act: -0.1700
Data Index: 1206674 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5059. Min Act: -0.1700
Data Index: 4630180 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5059. Min Act: -0.1700
Data Index: 5645014 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7871. Min Range: -4.7871
Max Act: 4.5059. Min Act: -0.1700
Data Index: 3219091 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19