Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.9951. Min Act: -0.1700
Data Index: 1380811 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.7139. Min Act: -0.1700
Data Index: 3766173 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.7139. Min Act: -0.1700
Data Index: 7618713 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.5889. Min Act: -0.1700
Data Index: 5105822 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.5576. Min Act: -0.1700
Data Index: 2496423 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.4014. Min Act: -0.1700
Data Index: 2135454 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.4014. Min Act: -0.1700
Data Index: 731889 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3701. Min Act: -0.1700
Data Index: 400976 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3389. Min Act: -0.1700
Data Index: 5234494 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3389. Min Act: -0.1700
Data Index: 3539937 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3389. Min Act: -0.1700
Data Index: 4007519 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3389. Min Act: -0.1700
Data Index: 2682849 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3389. Min Act: -0.1700
Data Index: 7632437 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.3076. Min Act: -0.1700
Data Index: 8100185 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.2764. Min Act: -0.1700
Data Index: 8710649 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.2764. Min Act: -0.1700
Data Index: 5189340 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.2451. Min Act: -0.1700
Data Index: 5479612 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.2451. Min Act: -0.1700
Data Index: 3383267 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.2764. Min Act: -0.1700
Data Index: 7221939 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9951. Min Range: -7.9951
Max Act: 7.2451. Min Act: -0.1700
Data Index: 5027107 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19