Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5498 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.4661. Min Act: -0.1700
Data Index: 557011 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.2785. Min Act: -0.1700
Data Index: 7824316 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.0285. Min Act: -0.1700
Data Index: 975808 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.9347. Min Act: -0.1700
Data Index: 7270896 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.9347. Min Act: -0.1700
Data Index: 6159990 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8722. Min Act: -0.1700
Data Index: 5564972 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.9034. Min Act: -0.1700
Data Index: 2821367 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8722. Min Act: -0.1700
Data Index: 7268881 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8722. Min Act: -0.1700
Data Index: 7440744 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8409. Min Act: -0.1700
Data Index: 3680196 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8409. Min Act: -0.1700
Data Index: 1585102 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 8789850 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4195453 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.7784. Min Act: -0.1700
Data Index: 7568714 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 274197 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4573603 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4899232 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 6960393 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.8096. Min Act: -0.1700
Data Index: 249328 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4661. Min Range: -4.4661
Max Act: 3.7784. Min Act: -0.1700
Data Index: 4788727 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19