Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2941 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.3777. Min Act: -0.1700
Data Index: 8170420 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.2840. Min Act: -0.1700
Data Index: 4210679 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.2840. Min Act: -0.1700
Data Index: 2242618 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.2527. Min Act: -0.1700
Data Index: 4431300 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.1902. Min Act: -0.1700
Data Index: 1673091 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.1590. Min Act: -0.1700
Data Index: 7856722 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0965. Min Act: -0.1700
Data Index: 6691899 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.1277. Min Act: -0.1700
Data Index: 4619852 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.1277. Min Act: -0.1700
Data Index: 1726194 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 8504794 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 2117556 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 370634 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 4210681 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 3483817 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0340. Min Act: -0.1700
Data Index: 2271581 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0652. Min Act: -0.1700
Data Index: 8313928 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0027. Min Act: -0.1700
Data Index: 7288310 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3777. Min Range: -7.3777
Max Act: 6.9715. Min Act: -0.1700
Data Index: 8455534 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0027. Min Act: -0.1700
Data Index: 7108747 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3777. Min Range: -7.3777
Max Act: 7.0027. Min Act: -0.1700
Data Index: 8166466 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19