Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 860 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.9201. Min Act: -0.1700
Data Index: 7929864 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.6076. Min Act: -0.1700
Data Index: 5924130 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.4826. Min Act: -0.1700
Data Index: 8585538 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.3576. Min Act: -0.1700
Data Index: 3293061 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.3576. Min Act: -0.1700
Data Index: 7527898 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.2951. Min Act: -0.1700
Data Index: 6651949 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.2951. Min Act: -0.1700
Data Index: 8082177 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.2951. Min Act: -0.1700
Data Index: 3462138 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.2951. Min Act: -0.1700
Data Index: 1898729 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1701. Min Act: -0.1700
Data Index: 7396374 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1701. Min Act: -0.1700
Data Index: 5986288 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1701. Min Act: -0.1700
Data Index: 91395 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1701. Min Act: -0.1700
Data Index: 6727473 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1701. Min Act: -0.1700
Data Index: 2907922 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1076. Min Act: -0.1700
Data Index: 956230 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1076. Min Act: -0.1700
Data Index: 8458732 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.1076. Min Act: -0.1700
Data Index: 2437688 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.0451. Min Act: -0.1700
Data Index: 4236989 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.0451. Min Act: -0.1700
Data Index: 5991147 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9201. Min Range: -9.9201
Max Act: 9.0451. Min Act: -0.1700
Data Index: 7975550 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19