Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5373 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1004. Min Range: -5.1004
Max Act: 5.1004. Min Act: -0.1700
Data Index: 3467104 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1004. Min Range: -5.1004
Max Act: 5.0067. Min Act: -0.1700
Data Index: 1800738 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9754. Min Act: -0.1700
Data Index: 3452008 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9442. Min Act: -0.1700
Data Index: 6231465 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9442. Min Act: -0.1700
Data Index: 4879435 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9129. Min Act: -0.1700
Data Index: 8078159 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9442. Min Act: -0.1700
Data Index: 687973 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9129. Min Act: -0.1700
Data Index: 3155686 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8817. Min Act: -0.1700
Data Index: 7337498 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9129. Min Act: -0.1700
Data Index: 1032855 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.9129. Min Act: -0.1700
Data Index: 7337500 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8817. Min Act: -0.1700
Data Index: 7337504 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8504. Min Act: -0.1700
Data Index: 2050211 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8504. Min Act: -0.1700
Data Index: 3848475 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8504. Min Act: -0.1700
Data Index: 8078158 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8504. Min Act: -0.1700
Data Index: 5683713 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8192. Min Act: -0.1700
Data Index: 3366011 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8192. Min Act: -0.1700
Data Index: 3439858 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8192. Min Act: -0.1700
Data Index: 2928091 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1004. Min Range: -5.1004
Max Act: 4.8504. Min Act: -0.1700
Data Index: 7337496 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19