Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.2929. Min Act: -0.1700
Data Index: 585779 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.2458. Min Act: -0.1700
Data Index: 7963684 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.2458. Min Act: -0.1700
Data Index: 7291372 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.2143. Min Act: -0.1700
Data Index: 1789708 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.2143. Min Act: -0.1700
Data Index: 4373763 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.2143. Min Act: -0.1700
Data Index: 1433162 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 3410157 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 3329679 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 4292237 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 1962509 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 1608373 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 857993 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 883027 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1986. Min Act: -0.1700
Data Index: 7353409 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1829. Min Act: -0.1700
Data Index: 3552126 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1829. Min Act: -0.1700
Data Index: 6455537 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1829. Min Act: -0.1700
Data Index: 1409482 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1829. Min Act: -0.1700
Data Index: 4520796 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1829. Min Act: -0.1700
Data Index: 3710291 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2929. Min Range: -3.2929
Max Act: 3.1672. Min Act: -0.1700
Data Index: 366485 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19