Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.3929. Min Act: -0.1700
Data Index: 5026174 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.3929. Min Act: -0.1700
Data Index: 3811997 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.3929. Min Act: -0.1700
Data Index: 3904424 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.3304. Min Act: -0.1700
Data Index: 2063421 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.3304. Min Act: -0.1700
Data Index: 6358126 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.2991. Min Act: -0.1700
Data Index: 6337966 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.2991. Min Act: -0.1700
Data Index: 1595249 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.3304. Min Act: -0.1700
Data Index: 3572741 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.2679. Min Act: -0.1700
Data Index: 1616041 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.2991. Min Act: -0.1700
Data Index: 481918 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.2366. Min Act: -0.1700
Data Index: 6969886 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.2366. Min Act: -0.1700
Data Index: 2045602 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1741. Min Act: -0.1700
Data Index: 2937754 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1741. Min Act: -0.1700
Data Index: 2098469 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1429. Min Act: -0.1700
Data Index: 3064860 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5791590 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1741. Min Act: -0.1700
Data Index: 4042644 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1429. Min Act: -0.1700
Data Index: 2578022 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1429. Min Act: -0.1700
Data Index: 2264807 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3929. Min Range: -5.3929
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5981548 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19