Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 365704 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.8565. Min Act: -0.1700
Data Index: 2253492 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.8252. Min Act: -0.1700
Data Index: 8716987 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.7002. Min Act: -0.1700
Data Index: 7576726 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.7002. Min Act: -0.1700
Data Index: 3073739 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.6065. Min Act: -0.1700
Data Index: 5038699 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.5752. Min Act: -0.1700
Data Index: 1985640 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.5752. Min Act: -0.1700
Data Index: 414691 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.5752. Min Act: -0.1700
Data Index: 1177081 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.5127. Min Act: -0.1700
Data Index: 130551 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.5440. Min Act: -0.1700
Data Index: 5049814 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4815. Min Act: -0.1700
Data Index: 298587 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4815. Min Act: -0.1700
Data Index: 1917975 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4815. Min Act: -0.1700
Data Index: 4090709 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4815. Min Act: -0.1700
Data Index: 7361064 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4815. Min Act: -0.1700
Data Index: 5465003 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4502. Min Act: -0.1700
Data Index: 1392201 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4502. Min Act: -0.1700
Data Index: 788202 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4502. Min Act: -0.1700
Data Index: 2668125 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9502. Min Range: -5.9502
Max Act: 5.4502. Min Act: -0.1700
Data Index: 1815650 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19