Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1527 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1229. Min Range: -5.1229
Max Act: 5.1229. Min Act: -0.1700
Data Index: 207281 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9979. Min Act: -0.1700
Data Index: 3334983 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9666. Min Act: -0.1700
Data Index: 1946715 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9979. Min Act: -0.1700
Data Index: 889812 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9666. Min Act: -0.1700
Data Index: 4277380 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9354. Min Act: -0.1700
Data Index: 453776 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9041. Min Act: -0.1700
Data Index: 8137644 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.9041. Min Act: -0.1700
Data Index: 3623486 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8729. Min Act: -0.1700
Data Index: 7065896 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8729. Min Act: -0.1700
Data Index: 7559708 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8729. Min Act: -0.1700
Data Index: 455393 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8729. Min Act: -0.1700
Data Index: 5062927 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8729. Min Act: -0.1700
Data Index: 301905 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8729. Min Act: -0.1700
Data Index: 54015 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8416. Min Act: -0.1700
Data Index: 2767765 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8416. Min Act: -0.1700
Data Index: 3158202 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8416. Min Act: -0.1700
Data Index: 3192472 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8104. Min Act: -0.1700
Data Index: 1795653 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8104. Min Act: -0.1700
Data Index: 3244519 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1229. Min Range: -5.1229
Max Act: 4.8104. Min Act: -0.1700
Data Index: 3453831 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19