Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5581 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1265. Min Range: -4.1265
Max Act: 4.1265. Min Act: -0.1700
Data Index: 6810962 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1265. Min Range: -4.1265
Max Act: 4.0640. Min Act: -0.1700
Data Index: 1090965 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1265. Min Range: -4.1265
Max Act: 4.0014. Min Act: -0.1700
Data Index: 2266528 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.9702. Min Act: -0.1700
Data Index: 302423 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.9702. Min Act: -0.1700
Data Index: 2286896 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.9702. Min Act: -0.1700
Data Index: 2249922 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.9389. Min Act: -0.1700
Data Index: 6961667 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8451. Min Act: -0.1700
Data Index: 6652316 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8764. Min Act: -0.1700
Data Index: 6784489 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8764. Min Act: -0.1700
Data Index: 7882242 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.9077. Min Act: -0.1700
Data Index: 3394544 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8451. Min Act: -0.1700
Data Index: 5461052 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8451. Min Act: -0.1700
Data Index: 7814227 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8138. Min Act: -0.1700
Data Index: 4754441 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.7826. Min Act: -0.1700
Data Index: 7203707 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8138. Min Act: -0.1700
Data Index: 2718872 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.8138. Min Act: -0.1700
Data Index: 1832891 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.7826. Min Act: -0.1700
Data Index: 2214819 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.7826. Min Act: -0.1700
Data Index: 784371 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1265. Min Range: -4.1265
Max Act: 3.7826. Min Act: -0.1700
Data Index: 531728 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19