Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6363 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3535. Min Range: -6.3535
Max Act: 6.3535. Min Act: -0.1700
Data Index: 8693609 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3535. Min Range: -6.3535
Max Act: 6.1660. Min Act: -0.1700
Data Index: 375750 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3535. Min Range: -6.3535
Max Act: 6.1348. Min Act: -0.1700
Data Index: 6046491 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3535. Min Range: -6.3535
Max Act: 6.0723. Min Act: -0.1700
Data Index: 71198 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.9785. Min Act: -0.1700
Data Index: 234257 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.9160. Min Act: -0.1700
Data Index: 4664862 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.8535. Min Act: -0.1700
Data Index: 1160761 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2687954 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7598. Min Act: -0.1700
Data Index: 4664864 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7598. Min Act: -0.1700
Data Index: 3648207 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7598. Min Act: -0.1700
Data Index: 8700201 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7285. Min Act: -0.1700
Data Index: 2432958 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7285. Min Act: -0.1700
Data Index: 5530366 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7598. Min Act: -0.1700
Data Index: 6338246 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.7285. Min Act: -0.1700
Data Index: 1124341 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.6973. Min Act: -0.1700
Data Index: 3004430 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.6973. Min Act: -0.1700
Data Index: 7181639 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.6973. Min Act: -0.1700
Data Index: 6418074 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.6660. Min Act: -0.1700
Data Index: 3563721 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3535. Min Range: -6.3535
Max Act: 5.6660. Min Act: -0.1700
Data Index: 6338248 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19