Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.3049. Min Act: -0.1700
Data Index: 1914733 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.3362. Min Act: -0.1700
Data Index: 2629734 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.3049. Min Act: -0.1700
Data Index: 8171633 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.1799. Min Act: -0.1700
Data Index: 6201686 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.1487. Min Act: -0.1700
Data Index: 7077999 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.1487. Min Act: -0.1700
Data Index: 6258038 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.1174. Min Act: -0.1700
Data Index: 4712112 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3949 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0862. Min Act: -0.1700
Data Index: 6457807 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0549. Min Act: -0.1700
Data Index: 2398373 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0862. Min Act: -0.1700
Data Index: 8744405 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.1174. Min Act: -0.1700
Data Index: 6602905 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0549. Min Act: -0.1700
Data Index: 3620157 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0549. Min Act: -0.1700
Data Index: 5022364 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0549. Min Act: -0.1700
Data Index: 994765 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0549. Min Act: -0.1700
Data Index: 4810632 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0237. Min Act: -0.1700
Data Index: 8168870 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0237. Min Act: -0.1700
Data Index: 1097503 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3362. Min Range: -5.3362
Max Act: 5.0237. Min Act: -0.1700
Data Index: 927734 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3362. Min Range: -5.3362
Max Act: 4.9924. Min Act: -0.1700
Data Index: 8510787 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19