Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0112. Min Range: -6.0112
Max Act: 6.0112. Min Act: -0.1700
Data Index: 152776 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.9800. Min Act: -0.1700
Data Index: 3083111 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.9487. Min Act: -0.1700
Data Index: 1969668 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4664878 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.9487. Min Act: -0.1700
Data Index: 3572104 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.8550. Min Act: -0.1700
Data Index: 4440164 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3923861 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.8237. Min Act: -0.1700
Data Index: 3316797 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.8237. Min Act: -0.1700
Data Index: 1624435 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.7925. Min Act: -0.1700
Data Index: 5914861 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.7925. Min Act: -0.1700
Data Index: 5969194 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.7925. Min Act: -0.1700
Data Index: 6167683 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.7612. Min Act: -0.1700
Data Index: 1747873 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5553955 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.6675. Min Act: -0.1700
Data Index: 2804767 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.6987. Min Act: -0.1700
Data Index: 5746975 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.6675. Min Act: -0.1700
Data Index: 7188969 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.6987. Min Act: -0.1700
Data Index: 4511648 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.6987. Min Act: -0.1700
Data Index: 1485565 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0112. Min Range: -6.0112
Max Act: 5.6675. Min Act: -0.1700
Data Index: 2376366 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19