Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1466 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.2043. Min Act: -0.1700
Data Index: 3392052 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1886. Min Act: -0.1700
Data Index: 8481033 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.2043. Min Act: -0.1700
Data Index: 7468291 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1729. Min Act: -0.1700
Data Index: 7390837 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1729. Min Act: -0.1700
Data Index: 4256796 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1729. Min Act: -0.1700
Data Index: 2568718 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1571. Min Act: -0.1700
Data Index: 7156720 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1414. Min Act: -0.1700
Data Index: 7091319 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1099. Min Act: -0.1700
Data Index: 34545 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1099. Min Act: -0.1700
Data Index: 1555320 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1099. Min Act: -0.1700
Data Index: 1865658 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1099. Min Act: -0.1700
Data Index: 5524733 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1099. Min Act: -0.1700
Data Index: 2241628 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1256. Min Act: -0.1700
Data Index: 1057698 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.1099. Min Act: -0.1700
Data Index: 1077071 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.0941. Min Act: -0.1700
Data Index: 8138377 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.0941. Min Act: -0.1700
Data Index: 8081960 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.0784. Min Act: -0.1700
Data Index: 3919641 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.0941. Min Act: -0.1700
Data Index: 4073118 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2043. Min Range: -3.2043
Max Act: 3.0784. Min Act: -0.1700
Data Index: 520151 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19