Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1867 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.5914. Min Act: -0.1700
Data Index: 3555930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.5289. Min Act: -0.1700
Data Index: 6743996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6004779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 8341079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4977. Min Act: -0.1700
Data Index: 3033291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 884159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 3317319 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 3127485 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 4679062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 2852789 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 8756317 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 1080379 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 4523531 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 6580600 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 6371642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4352. Min Act: -0.1700
Data Index: 4689063 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4352. Min Act: -0.1700
Data Index: 1223269 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4352. Min Act: -0.1700
Data Index: 5304630 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4352. Min Act: -0.1700
Data Index: 3116580 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4352. Min Act: -0.1700
Data Index: 1609063 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19