Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 68 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.4798. Min Act: -0.1700
Data Index: 2572279 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.4798. Min Act: -0.1700
Data Index: 6801792 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.4486. Min Act: -0.1700
Data Index: 6070298 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.3548. Min Act: -0.1700
Data Index: 5846241 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.1986. Min Act: -0.1700
Data Index: 1609674 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.1361. Min Act: -0.1700
Data Index: 4192463 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.1048. Min Act: -0.1700
Data Index: 4817159 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.1048. Min Act: -0.1700
Data Index: 1153794 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.0736. Min Act: -0.1700
Data Index: 4790076 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.0736. Min Act: -0.1700
Data Index: 3030725 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.0111. Min Act: -0.1700
Data Index: 3214671 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.0423. Min Act: -0.1700
Data Index: 5581478 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4798. Min Range: -6.4798
Max Act: 6.0111. Min Act: -0.1700
Data Index: 927707 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9798. Min Act: -0.1700
Data Index: 4041770 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9486. Min Act: -0.1700
Data Index: 5353148 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9486. Min Act: -0.1700
Data Index: 3741120 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9173. Min Act: -0.1700
Data Index: 852454 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9173. Min Act: -0.1700
Data Index: 2768011 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9173. Min Act: -0.1700
Data Index: 5822841 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4798. Min Range: -6.4798
Max Act: 5.9173. Min Act: -0.1700
Data Index: 1558029 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19