Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2699. Min Range: -9.2699
Max Act: 9.2699. Min Act: -0.1700
Data Index: 3005113 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2699. Min Range: -9.2699
Max Act: 9.2074. Min Act: -0.1700
Data Index: 4028116 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.9574. Min Act: -0.1700
Data Index: 6849589 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2699. Min Range: -9.2699
Max Act: 9.0199. Min Act: -0.1700
Data Index: 1158213 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.8949. Min Act: -0.1700
Data Index: 7963517 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.8949. Min Act: -0.1700
Data Index: 1377815 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.8949. Min Act: -0.1700
Data Index: 2918742 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.8324. Min Act: -0.1700
Data Index: 7680545 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7699. Min Act: -0.1700
Data Index: 5681551 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7074. Min Act: -0.1700
Data Index: 8471298 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7074. Min Act: -0.1700
Data Index: 4503240 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7699. Min Act: -0.1700
Data Index: 4070655 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7699. Min Act: -0.1700
Data Index: 7124438 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7699. Min Act: -0.1700
Data Index: 3627949 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7699. Min Act: -0.1700
Data Index: 3910915 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7074. Min Act: -0.1700
Data Index: 1421726 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7074. Min Act: -0.1700
Data Index: 6006921 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7074. Min Act: -0.1700
Data Index: 552752 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.7074. Min Act: -0.1700
Data Index: 3876261 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2699. Min Range: -9.2699
Max Act: 8.6449. Min Act: -0.1700
Data Index: 1092150 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19