Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5080 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.3362. Min Act: -0.1672
Data Index: 2415222 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.2737. Min Act: -0.1700
Data Index: 5735 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.2737. Min Act: -0.1700
Data Index: 7632240 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.2112. Min Act: -0.1700
Data Index: 8285457 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.1487. Min Act: -0.1696
Data Index: 5736 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.1487. Min Act: -0.1700
Data Index: 1474784 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.1487. Min Act: -0.1700
Data Index: 4753928 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.0862. Min Act: -0.1698
Data Index: 492232 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.1487. Min Act: -0.1700
Data Index: 7222634 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.0862. Min Act: -0.1700
Data Index: 6836234 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3362. Min Range: -9.3362
Max Act: 9.0237. Min Act: -0.1697
Data Index: 2528928 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.9612. Min Act: -0.1700
Data Index: 2537570 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.9612. Min Act: -0.1700
Data Index: 3169212 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.9612. Min Act: -0.1700
Data Index: 8690479 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.8987. Min Act: -0.1700
Data Index: 2051144 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.8987. Min Act: -0.1696
Data Index: 2219960 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.8987. Min Act: -0.1700
Data Index: 1332371 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.8987. Min Act: -0.1700
Data Index: 1053288 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.8987. Min Act: -0.1698
Data Index: 71249 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3362. Min Range: -9.3362
Max Act: 8.8362. Min Act: -0.1677
Data Index: 3119473 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19