Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0710. Min Range: -13.0710
Max Act: 13.0710. Min Act: -0.1700
Data Index: 2980280 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.7585. Min Act: -0.1700
Data Index: 2030538 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.6335. Min Act: -0.1700
Data Index: 5904283 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.5710. Min Act: -0.1700
Data Index: 5131082 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.4460. Min Act: -0.1700
Data Index: 2519068 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.3210. Min Act: -0.1700
Data Index: 4142325 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.3835. Min Act: -0.1700
Data Index: 4168023 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.1960. Min Act: -0.1700
Data Index: 5659410 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.1335. Min Act: -0.1700
Data Index: 2526003 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.0710. Min Act: -0.1699
Data Index: 4596640 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.0710. Min Act: -0.1700
Data Index: 4391939 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0710. Min Range: -13.0710
Max Act: 12.0710. Min Act: -0.1700
Data Index: 4570049 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.9460. Min Act: -0.1700
Data Index: 4981718 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.9460. Min Act: -0.1700
Data Index: 8012017 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.9460. Min Act: -0.1700
Data Index: 8486598 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.8835. Min Act: -0.1700
Data Index: 372760 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.8835. Min Act: -0.1700
Data Index: 7863913 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.8210. Min Act: -0.1700
Data Index: 1989681 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.8210. Min Act: -0.1700
Data Index: 2519072 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0710. Min Range: -13.0710
Max Act: 11.8835. Min Act: -0.1700
Data Index: 7793714 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19