Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8662. Min Act: -0.1700
Data Index: 1982110 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8349. Min Act: -0.1700
Data Index: 2200610 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8349. Min Act: -0.1700
Data Index: 5574654 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8349. Min Act: -0.1700
Data Index: 2099419 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8037. Min Act: -0.1700
Data Index: 6437349 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8037. Min Act: -0.1700
Data Index: 3127583 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.8037. Min Act: -0.1700
Data Index: 7328271 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 618094 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 5673944 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 1855209 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 6933786 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 3089163 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7412. Min Act: -0.1700
Data Index: 7354823 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7412. Min Act: -0.1700
Data Index: 663190 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7412. Min Act: -0.1700
Data Index: 6584150 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7412. Min Act: -0.1700
Data Index: 6466699 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7099. Min Act: -0.1700
Data Index: 618098 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7099. Min Act: -0.1700
Data Index: 2121815 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7099. Min Act: -0.1700
Data Index: 663191 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8662. Min Range: -4.8662
Max Act: 4.7099. Min Act: -0.1700
Data Index: 6340450 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19