Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5603. Min Act: -0.1700
Data Index: 7675040 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5603. Min Act: -0.1700
Data Index: 2428404 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 4035478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 6690951 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 6176176 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 2932197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 5627365 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 8753221 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 4999344 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 8658710 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 2171856 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 4527000 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.5289. Min Act: -0.1700
Data Index: 7240150 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 5734756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 5848212 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 2734319 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 3245879 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 6043350 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 3729023 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5603. Min Range: -3.5603
Max Act: 3.4976. Min Act: -0.1700
Data Index: 110429 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19