Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.6520. Min Act: -0.1700
Data Index: 8299088 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.6364. Min Act: -0.1700
Data Index: 7884358 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.6051. Min Act: -0.1700
Data Index: 560818 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5268. Min Act: -0.1700
Data Index: 5795520 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5268. Min Act: -0.1700
Data Index: 6129708 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4955. Min Act: -0.1700
Data Index: 205704 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5111. Min Act: -0.1700
Data Index: 5464913 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5111. Min Act: -0.1700
Data Index: 1224370 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5111. Min Act: -0.1700
Data Index: 3589217 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5111. Min Act: -0.1700
Data Index: 2649776 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4955. Min Act: -0.1700
Data Index: 7162771 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4955. Min Act: -0.1700
Data Index: 1637101 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4955. Min Act: -0.1700
Data Index: 7628016 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.5111. Min Act: -0.1700
Data Index: 313283 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4798. Min Act: -0.1700
Data Index: 3581412 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4798. Min Act: -0.1700
Data Index: 8169710 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4798. Min Act: -0.1700
Data Index: 3336017 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4641. Min Act: -0.1700
Data Index: 8726629 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4485. Min Act: -0.1700
Data Index: 3043905 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6520. Min Range: -3.6520
Max Act: 3.4485. Min Act: -0.1700
Data Index: 2820364 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19