Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5712 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.5859. Min Act: -0.1700
Data Index: 5668333 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.5234. Min Act: -0.1700
Data Index: 8586800 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4922. Min Act: -0.1700
Data Index: 2680896 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4297. Min Act: -0.1700
Data Index: 2423168 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4297. Min Act: -0.1700
Data Index: 4766203 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4297. Min Act: -0.1700
Data Index: 5383528 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4297. Min Act: -0.1700
Data Index: 7013676 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4297. Min Act: -0.1700
Data Index: 574079 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.4297. Min Act: -0.1700
Data Index: 622092 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3984. Min Act: -0.1700
Data Index: 3065154 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3984. Min Act: -0.1700
Data Index: 1964638 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3984. Min Act: -0.1700
Data Index: 5379376 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3984. Min Act: -0.1700
Data Index: 3995428 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3984. Min Act: -0.1700
Data Index: 7289934 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3984. Min Act: -0.1700
Data Index: 5011614 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3672. Min Act: -0.1700
Data Index: 6747238 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3672. Min Act: -0.1700
Data Index: 8802204 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3359. Min Act: -0.1700
Data Index: 3232167 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3672. Min Act: -0.1700
Data Index: 1778642 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5859. Min Range: -4.5859
Max Act: 4.3672. Min Act: -0.1700
Data Index: 186443 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19