Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1419. Min Range: -9.1419
Max Act: 9.1419. Min Act: -0.1700
Data Index: 1725630 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.7044. Min Act: -0.1700
Data Index: 2599886 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.4544. Min Act: -0.1700
Data Index: 6635742 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.3294. Min Act: -0.1700
Data Index: 8163334 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.2669. Min Act: -0.1700
Data Index: 6532500 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.2357. Min Act: -0.1700
Data Index: 1210621 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.1732. Min Act: -0.1700
Data Index: 6341681 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.2044. Min Act: -0.1700
Data Index: 3802546 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.1419. Min Act: -0.1700
Data Index: 4937037 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.1419. Min Act: -0.1700
Data Index: 38089 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.1107. Min Act: -0.1700
Data Index: 14838 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.0794. Min Act: -0.1700
Data Index: 6339674 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.1107. Min Act: -0.1700
Data Index: 4130365 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.0794. Min Act: -0.1700
Data Index: 613484 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.0482. Min Act: -0.1700
Data Index: 4077325 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1419. Min Range: -9.1419
Max Act: 8.0169. Min Act: -0.1700
Data Index: 3850286 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1419. Min Range: -9.1419
Max Act: 7.9857. Min Act: -0.1700
Data Index: 6635753 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1419. Min Range: -9.1419
Max Act: 7.9544. Min Act: -0.1700
Data Index: 76158 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1419. Min Range: -9.1419
Max Act: 7.9232. Min Act: -0.1700
Data Index: 4254297 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1419. Min Range: -9.1419
Max Act: 7.8294. Min Act: -0.1700
Data Index: 3375787 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19