Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2367. Min Range: -8.2367
Max Act: 8.2367. Min Act: -0.1700
Data Index: 3703361 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2367. Min Range: -8.2367
Max Act: 8.2367. Min Act: -0.1700
Data Index: 1722605 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.9867. Min Act: -0.1700
Data Index: 1531966 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.6117. Min Act: -0.1700
Data Index: 732745 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.5805. Min Act: -0.1700
Data Index: 7860015 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.5180. Min Act: -0.1700
Data Index: 3703360 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.4867. Min Act: -0.1700
Data Index: 8109867 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2992. Min Act: -0.1700
Data Index: 3793567 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.3305. Min Act: -0.1700
Data Index: 5643446 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2992. Min Act: -0.1700
Data Index: 4635467 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2680. Min Act: -0.1700
Data Index: 7971613 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2367. Min Act: -0.1700
Data Index: 2931668 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2680. Min Act: -0.1700
Data Index: 5065359 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2680. Min Act: -0.1700
Data Index: 8756180 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.2055. Min Act: -0.1700
Data Index: 419890 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.1117. Min Act: -0.1700
Data Index: 2782177 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.1117. Min Act: -0.1700
Data Index: 6948597 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.1430. Min Act: -0.1700
Data Index: 6415580 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.1430. Min Act: -0.1700
Data Index: 340360 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2367. Min Range: -8.2367
Max Act: 7.0180. Min Act: -0.1700
Data Index: 5106922 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19