Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5062. Min Range: -11.5062
Max Act: 11.5062. Min Act: -0.1700
Data Index: 3513876 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5062. Min Range: -11.5062
Max Act: 11.0062. Min Act: -0.1700
Data Index: 8245158 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.9437. Min Act: -0.1700
Data Index: 5305935 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.9437. Min Act: -0.1700
Data Index: 3742407 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.8812. Min Act: -0.1700
Data Index: 3223674 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.8187. Min Act: -0.1700
Data Index: 2801626 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.8187. Min Act: -0.1700
Data Index: 4395035 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.6937. Min Act: -0.1700
Data Index: 5617379 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.6937. Min Act: -0.1700
Data Index: 4766843 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.6312. Min Act: -0.1700
Data Index: 2350416 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5687. Min Act: -0.1700
Data Index: 8359693 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5687. Min Act: -0.1700
Data Index: 2195853 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5687. Min Act: -0.1700
Data Index: 5774721 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5687. Min Act: -0.1700
Data Index: 1598688 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5062. Min Act: -0.1700
Data Index: 7091871 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5062. Min Act: -0.1700
Data Index: 7091870 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.5062. Min Act: -0.1700
Data Index: 2181788 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.4437. Min Act: -0.1700
Data Index: 1982659 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.4437. Min Act: -0.1700
Data Index: 7091876 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5062. Min Range: -11.5062
Max Act: 10.4437. Min Act: -0.1700
Data Index: 6071664 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19