Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0973. Min Act: -0.1700
Data Index: 4479309 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0973. Min Act: -0.1700
Data Index: 5015797 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0660. Min Act: -0.1700
Data Index: 7141935 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0660. Min Act: -0.1700
Data Index: 4740131 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0348. Min Act: -0.1700
Data Index: 8253962 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0348. Min Act: -0.1700
Data Index: 7059479 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0973. Min Range: -5.0973
Max Act: 5.0035. Min Act: -0.1700
Data Index: 8134533 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9723. Min Act: -0.1700
Data Index: 7472706 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9723. Min Act: -0.1700
Data Index: 2650227 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9410. Min Act: -0.1700
Data Index: 7442823 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9723. Min Act: -0.1700
Data Index: 6316641 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9098. Min Act: -0.1700
Data Index: 6910391 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9410. Min Act: -0.1700
Data Index: 1527759 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9098. Min Act: -0.1700
Data Index: 3801078 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.9098. Min Act: -0.1700
Data Index: 6217081 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.8785. Min Act: -0.1700
Data Index: 2526161 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.8785. Min Act: -0.1700
Data Index: 5863602 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.8785. Min Act: -0.1700
Data Index: 669494 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.8785. Min Act: -0.1700
Data Index: 8037638 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0973. Min Range: -5.0973
Max Act: 4.8785. Min Act: -0.1700
Data Index: 4470970 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19