Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0783. Min Range: -10.0783
Max Act: 10.0783. Min Act: -0.1700
Data Index: 820396 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0783. Min Range: -10.0783
Max Act: 10.0783. Min Act: -0.1700
Data Index: 4766721 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.8908. Min Act: -0.1700
Data Index: 1538287 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.6408. Min Act: -0.1700
Data Index: 5026727 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.6408. Min Act: -0.1700
Data Index: 1200651 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.5158. Min Act: -0.1700
Data Index: 6471426 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.4533. Min Act: -0.1700
Data Index: 8216229 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.5158. Min Act: -0.1700
Data Index: 3833917 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.4533. Min Act: -0.1700
Data Index: 3761268 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.3908. Min Act: -0.1700
Data Index: 7481692 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.3283. Min Act: -0.1700
Data Index: 4811021 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.2658. Min Act: -0.1700
Data Index: 4214263 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.2658. Min Act: -0.1700
Data Index: 7495535 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.2658. Min Act: -0.1700
Data Index: 8155054 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.2658. Min Act: -0.1700
Data Index: 771918 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.2658. Min Act: -0.1700
Data Index: 2384678 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.2033. Min Act: -0.1700
Data Index: 4308980 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.1408. Min Act: -0.1700
Data Index: 650185 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.0783. Min Act: -0.1700
Data Index: 6649454 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0783. Min Range: -10.0783
Max Act: 9.1408. Min Act: -0.1700
Data Index: 5335977 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19