Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2841 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.8192. Min Act: -0.1700
Data Index: 4992535 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.7880. Min Act: -0.1700
Data Index: 7413691 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.7567. Min Act: -0.1700
Data Index: 6566694 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.7255. Min Act: -0.1700
Data Index: 6700426 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.6630. Min Act: -0.1700
Data Index: 3918675 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.6317. Min Act: -0.1700
Data Index: 6746143 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.6005. Min Act: -0.1700
Data Index: 880697 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.6005. Min Act: -0.1700
Data Index: 5239561 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5692. Min Act: -0.1700
Data Index: 5621112 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.6005. Min Act: -0.1700
Data Index: 1074197 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5692. Min Act: -0.1700
Data Index: 2110821 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5692. Min Act: -0.1700
Data Index: 7830927 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5067. Min Act: -0.1700
Data Index: 7255173 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5380. Min Act: -0.1700
Data Index: 8782373 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5380. Min Act: -0.1700
Data Index: 3984053 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5692. Min Act: -0.1700
Data Index: 3835169 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5380. Min Act: -0.1700
Data Index: 5857256 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5067. Min Act: -0.1700
Data Index: 1242291 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.5067. Min Act: -0.1700
Data Index: 4874186 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8192. Min Range: -6.8192
Max Act: 6.4755. Min Act: -0.1700
Data Index: 4632623 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19