Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.9969. Min Act: -0.1700
Data Index: 7453714 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.8719. Min Act: -0.1700
Data Index: 487419 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.8719. Min Act: -0.1700
Data Index: 756213 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.8094. Min Act: -0.1700
Data Index: 1534308 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7782. Min Act: -0.1700
Data Index: 4089067 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7469. Min Act: -0.1700
Data Index: 1329048 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.8094. Min Act: -0.1700
Data Index: 5676058 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7782. Min Act: -0.1700
Data Index: 6160800 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7782. Min Act: -0.1700
Data Index: 3483296 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7782. Min Act: -0.1700
Data Index: 1631388 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7469. Min Act: -0.1700
Data Index: 3409650 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7157. Min Act: -0.1700
Data Index: 912131 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7157. Min Act: -0.1700
Data Index: 3559375 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.7157. Min Act: -0.1700
Data Index: 3269336 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.6844. Min Act: -0.1700
Data Index: 439675 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.6844. Min Act: -0.1700
Data Index: 569685 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.6844. Min Act: -0.1700
Data Index: 2949488 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.6844. Min Act: -0.1700
Data Index: 3839006 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.6844. Min Act: -0.1700
Data Index: 5721300 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9969. Min Range: -4.9969
Max Act: 4.6532. Min Act: -0.1700
Data Index: 4302999 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19