Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0723. Min Range: -4.0723
Max Act: 4.0723. Min Act: -0.1700
Data Index: 3821624 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6658. Min Act: -0.1700
Data Index: 1162986 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6658. Min Act: -0.1700
Data Index: 971498 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6502. Min Act: -0.1700
Data Index: 7362687 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6189. Min Act: -0.1700
Data Index: 6612929 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6032. Min Act: -0.1700
Data Index: 8297409 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6189. Min Act: -0.1700
Data Index: 6544348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6189. Min Act: -0.1700
Data Index: 526907 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6189. Min Act: -0.1700
Data Index: 7689623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 6176517 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6189. Min Act: -0.1700
Data Index: 3311861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 810466 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6032. Min Act: -0.1700
Data Index: 2170914 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 8718867 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 1281030 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 1996607 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 6138085 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5876. Min Act: -0.1700
Data Index: 4439913 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5719. Min Act: -0.1700
Data Index: 7591513 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.5719. Min Act: -0.1700
Data Index: 3042933 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19