Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3948 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.9957. Min Act: -0.1700
Data Index: 3138595 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.8394. Min Act: -0.1700
Data Index: 103264 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.8082. Min Act: -0.1700
Data Index: 2041013 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.7769. Min Act: -0.1700
Data Index: 7673846 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.7769. Min Act: -0.1700
Data Index: 7136381 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.6832. Min Act: -0.1700
Data Index: 3296170 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.6832. Min Act: -0.1700
Data Index: 2072285 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.6832. Min Act: -0.1700
Data Index: 8114046 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.6519. Min Act: -0.1700
Data Index: 6822520 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.6207. Min Act: -0.1700
Data Index: 1485124 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5894. Min Act: -0.1700
Data Index: 7715940 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5894. Min Act: -0.1700
Data Index: 4177593 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5894. Min Act: -0.1700
Data Index: 606541 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5894. Min Act: -0.1700
Data Index: 6017906 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.6207. Min Act: -0.1700
Data Index: 1699558 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5582. Min Act: -0.1700
Data Index: 2944964 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5582. Min Act: -0.1700
Data Index: 4315528 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5582. Min Act: -0.1700
Data Index: 3030580 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5269. Min Act: -0.1700
Data Index: 7000622 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.5269. Min Act: -0.1700
Data Index: 5279125 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19