Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.3667. Min Act: -0.1700
Data Index: 610617 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.3667. Min Act: -0.1700
Data Index: 610621 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.3354. Min Act: -0.1700
Data Index: 442626 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.2729. Min Act: -0.1700
Data Index: 4453933 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.2729. Min Act: -0.1700
Data Index: 7890252 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.2417. Min Act: -0.1700
Data Index: 610616 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.2104. Min Act: -0.1700
Data Index: 7361636 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.1792. Min Act: -0.1700
Data Index: 1816626 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.1792. Min Act: -0.1700
Data Index: 442627 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.1792. Min Act: -0.1700
Data Index: 7890257 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.1479. Min Act: -0.1700
Data Index: 3292899 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.1479. Min Act: -0.1700
Data Index: 1431985 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1810956 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0854. Min Act: -0.1700
Data Index: 4453932 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0542. Min Act: -0.1700
Data Index: 1205525 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0542. Min Act: -0.1700
Data Index: 149148 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0229. Min Act: -0.1700
Data Index: 4735086 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0229. Min Act: -0.1700
Data Index: 1060214 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0229. Min Act: -0.1700
Data Index: 7752573 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3667. Min Range: -6.3667
Max Act: 6.0229. Min Act: -0.1700
Data Index: 6311925 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19