Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4884. Min Range: -8.4884
Max Act: 8.4884. Min Act: -0.1700
Data Index: 4183169 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.4884. Min Act: -0.1700
Data Index: 7407780 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.4259. Min Act: -0.1700
Data Index: 8261390 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.4259. Min Act: -0.1700
Data Index: 8761220 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.3009. Min Act: -0.1700
Data Index: 2532868 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.2697. Min Act: -0.1700
Data Index: 5360894 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.2072. Min Act: -0.1700
Data Index: 6005402 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.2072. Min Act: -0.1700
Data Index: 3371171 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.2072. Min Act: -0.1700
Data Index: 5149520 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.1759. Min Act: -0.1700
Data Index: 446106 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.1447. Min Act: -0.1700
Data Index: 3446035 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.1759. Min Act: -0.1700
Data Index: 7638951 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.1134. Min Act: -0.1700
Data Index: 6131570 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.0822. Min Act: -0.1700
Data Index: 1276791 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.0822. Min Act: -0.1700
Data Index: 2388247 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.1134. Min Act: -0.1700
Data Index: 8586471 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.1134. Min Act: -0.1700
Data Index: 364475 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.0509. Min Act: -0.1700
Data Index: 5597108 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.0509. Min Act: -0.1700
Data Index: 5675612 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4884. Min Range: -8.4884
Max Act: 7.0197. Min Act: -0.1700
Data Index: 7558297 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19