Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 701 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0604. Min Range: -5.0604
Max Act: 5.0604. Min Act: -0.1700
Data Index: 6837664 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9979. Min Act: -0.1700
Data Index: 3439132 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0604. Min Range: -5.0604
Max Act: 5.0292. Min Act: -0.1700
Data Index: 1571813 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9667. Min Act: -0.1700
Data Index: 4418631 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9979. Min Act: -0.1699
Data Index: 1220582 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7499387 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7344884 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1672251 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 7426319 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 5311535 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 8595113 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 809953 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1401030 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 2195176 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9354. Min Act: -0.1700
Data Index: 7910072 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9042. Min Act: -0.1700
Data Index: 1572554 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9042. Min Act: -0.1700
Data Index: 6209233 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.9042. Min Act: -0.1700
Data Index: 1144738 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.8729. Min Act: -0.1700
Data Index: 4261344 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0604. Min Range: -5.0604
Max Act: 4.8729. Min Act: -0.1700
Data Index: 1236696 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19