Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1841. Min Range: -6.1841
Max Act: 6.1841. Min Act: -0.1700
Data Index: 5157895 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1841. Min Range: -6.1841
Max Act: 6.1216. Min Act: -0.1700
Data Index: 7423788 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1841. Min Range: -6.1841
Max Act: 6.1216. Min Act: -0.1700
Data Index: 1260631 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1841. Min Range: -6.1841
Max Act: 6.1216. Min Act: -0.1700
Data Index: 6489110 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7791407 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.9654. Min Act: -0.1700
Data Index: 5312495 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.9966. Min Act: -0.1700
Data Index: 3601125 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.9654. Min Act: -0.1700
Data Index: 1856139 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.8716. Min Act: -0.1700
Data Index: 3696259 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.8716. Min Act: -0.1700
Data Index: 595045 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.8404. Min Act: -0.1700
Data Index: 3552568 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7779. Min Act: -0.1700
Data Index: 4560322 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7779. Min Act: -0.1700
Data Index: 609407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7779. Min Act: -0.1700
Data Index: 2743450 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7779. Min Act: -0.1700
Data Index: 7794150 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7466. Min Act: -0.1700
Data Index: 5532969 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7466. Min Act: -0.1700
Data Index: 8532426 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7466. Min Act: -0.1700
Data Index: 3830030 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7466. Min Act: -0.1700
Data Index: 4892376 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1841. Min Range: -6.1841
Max Act: 5.7466. Min Act: -0.1700
Data Index: 3558001 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19