Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.7228. Min Act: -0.1700
Data Index: 4774478 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.5820. Min Act: -0.1700
Data Index: 8200809 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.5663. Min Act: -0.1700
Data Index: 8343589 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.5350. Min Act: -0.1700
Data Index: 7622348 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.5350. Min Act: -0.1700
Data Index: 6002608 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.5194. Min Act: -0.1700
Data Index: 7622353 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4880. Min Act: -0.1700
Data Index: 906517 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4880. Min Act: -0.1700
Data Index: 6737315 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4880. Min Act: -0.1700
Data Index: 8210896 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4724. Min Act: -0.1700
Data Index: 1163472 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4567. Min Act: -0.1700
Data Index: 3294008 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4724. Min Act: -0.1700
Data Index: 906518 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4724. Min Act: -0.1700
Data Index: 5801543 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4410. Min Act: -0.1700
Data Index: 6737310 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4567. Min Act: -0.1700
Data Index: 7890780 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4410. Min Act: -0.1700
Data Index: 8424776 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4097. Min Act: -0.1700
Data Index: 1306911 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4254. Min Act: -0.1700
Data Index: 1158304 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.4097. Min Act: -0.1700
Data Index: 2823755 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7228. Min Range: -3.7228
Max Act: 3.3940. Min Act: -0.1700
Data Index: 6375465 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19