Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3839 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.8539. Min Act: -0.1700
Data Index: 6663557 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.7914. Min Act: -0.1700
Data Index: 7430049 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.7914. Min Act: -0.1700
Data Index: 8090410 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.7289. Min Act: -0.1700
Data Index: 2725850 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.7289. Min Act: -0.1700
Data Index: 7914877 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.7914. Min Act: -0.1700
Data Index: 5779928 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.6664. Min Act: -0.1700
Data Index: 5896978 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.6039. Min Act: -0.1700
Data Index: 318774 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.6039. Min Act: -0.1700
Data Index: 2001502 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.6039. Min Act: -0.1700
Data Index: 2803000 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.5414. Min Act: -0.1700
Data Index: 5187502 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.5414. Min Act: -0.1700
Data Index: 1600612 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.5414. Min Act: -0.1700
Data Index: 1947568 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.5414. Min Act: -0.1700
Data Index: 6287896 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.4789. Min Act: -0.1700
Data Index: 3406369 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.4789. Min Act: -0.1700
Data Index: 7204747 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.3539. Min Act: -0.1700
Data Index: 603763 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.3539. Min Act: -0.1700
Data Index: 6399174 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.4164. Min Act: -0.1700
Data Index: 579255 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8539. Min Range: -9.8539
Max Act: 9.3539. Min Act: -0.1700
Data Index: 6332621 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19