Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2258 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 4187854 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9493. Min Act: -0.1700
Data Index: 4437250 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9181. Min Act: -0.1700
Data Index: 4658764 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9181. Min Act: -0.1700
Data Index: 1784774 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9181. Min Act: -0.1700
Data Index: 501828 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8868. Min Act: -0.1700
Data Index: 6391527 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8868. Min Act: -0.1700
Data Index: 7053336 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8243. Min Act: -0.1700
Data Index: 355756 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8868. Min Act: -0.1700
Data Index: 5464297 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 4138422 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 7962909 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 8300017 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8243. Min Act: -0.1700
Data Index: 3927910 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 3944111 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 4112947 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8243. Min Act: -0.1700
Data Index: 6518260 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8243. Min Act: -0.1700
Data Index: 1805984 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7931. Min Act: -0.1700
Data Index: 5355121 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7931. Min Act: -0.1700
Data Index: 2326842 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7931. Min Act: -0.1700
Data Index: 501826 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19