Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5081 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.3764. Min Act: -0.1700
Data Index: 986360 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.1264. Min Act: -0.1700
Data Index: 7366866 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.1264. Min Act: -0.1700
Data Index: 3809233 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.0639. Min Act: -0.1700
Data Index: 864040 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.0639. Min Act: -0.1700
Data Index: 2364648 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.0639. Min Act: -0.1700
Data Index: 3136012 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.0014. Min Act: -0.1700
Data Index: 7748989 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.0014. Min Act: -0.1700
Data Index: 6503819 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3764. Min Range: -8.3764
Max Act: 8.0014. Min Act: -0.1700
Data Index: 8371178 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.9389. Min Act: -0.1700
Data Index: 2044277 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.9389. Min Act: -0.1700
Data Index: 8464619 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.8764. Min Act: -0.1700
Data Index: 8654137 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.8764. Min Act: -0.1700
Data Index: 2187314 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.8139. Min Act: -0.1700
Data Index: 3715781 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.7514. Min Act: -0.1700
Data Index: 6480 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.7514. Min Act: -0.1700
Data Index: 2554786 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.7514. Min Act: -0.1700
Data Index: 1681825 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.7514. Min Act: -0.1700
Data Index: 2073220 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.6889. Min Act: -0.1700
Data Index: 5246224 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3764. Min Range: -8.3764
Max Act: 7.6889. Min Act: -0.1700
Data Index: 4699341 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19