Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 520 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.6921. Min Act: -0.1700
Data Index: 5313552 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.6296. Min Act: -0.1700
Data Index: 1952856 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.6296. Min Act: -0.1700
Data Index: 1738416 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5671. Min Act: -0.1700
Data Index: 8182497 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5046. Min Act: -0.1700
Data Index: 975154 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5358. Min Act: -0.1700
Data Index: 5730098 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5046. Min Act: -0.1700
Data Index: 3431542 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 4710662 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 5730093 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5046. Min Act: -0.1700
Data Index: 8462356 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5046. Min Act: -0.1700
Data Index: 1183003 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.5046. Min Act: -0.1700
Data Index: 5853189 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 8605385 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 5896190 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 5730099 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4421. Min Act: -0.1700
Data Index: 2224636 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 4892905 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 5164196 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4733. Min Act: -0.1700
Data Index: 4541969 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6921. Min Range: -4.6921
Max Act: 4.4421. Min Act: -0.1700
Data Index: 2706825 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19