Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1404. Min Range: -4.1404
Max Act: 4.1404. Min Act: -0.1700
Data Index: 3240628 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7965. Min Act: -0.1700
Data Index: 4337032 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7183. Min Act: -0.1700
Data Index: 274909 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6870. Min Act: -0.1700
Data Index: 8636091 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6870. Min Act: -0.1700
Data Index: 6604735 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6714. Min Act: -0.1700
Data Index: 6621263 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6714. Min Act: -0.1700
Data Index: 4338867 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6401. Min Act: -0.1700
Data Index: 4050220 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6088. Min Act: -0.1700
Data Index: 6179325 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5775. Min Act: -0.1700
Data Index: 1769687 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5931. Min Act: -0.1700
Data Index: 3958057 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5618. Min Act: -0.1700
Data Index: 3890697 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5618. Min Act: -0.1700
Data Index: 1959834 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5618. Min Act: -0.1700
Data Index: 5256329 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5618. Min Act: -0.1700
Data Index: 6213765 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5618. Min Act: -0.1700
Data Index: 2898834 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5305. Min Act: -0.1700
Data Index: 7365206 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5462. Min Act: -0.1700
Data Index: 5007014 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5462. Min Act: -0.1700
Data Index: 4317263 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.5462. Min Act: -0.1700
Data Index: 8298626 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19