Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.7127. Min Act: -0.1700
Data Index: 1350553 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.7127. Min Act: -0.1700
Data Index: 6303498 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.5877. Min Act: -0.1700
Data Index: 715722 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.3377. Min Act: -0.1700
Data Index: 8011028 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.3377. Min Act: -0.1700
Data Index: 5574576 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.1189. Min Act: -0.1700
Data Index: 3610103 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.0877. Min Act: -0.1700
Data Index: 2992418 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.0877. Min Act: -0.1700
Data Index: 1826116 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.0252. Min Act: -0.1700
Data Index: 5463473 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7127. Min Range: -8.7127
Max Act: 8.0252. Min Act: -0.1700
Data Index: 2732448 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9627. Min Act: -0.1700
Data Index: 5905000 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9627. Min Act: -0.1700
Data Index: 1099545 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9315. Min Act: -0.1700
Data Index: 6061183 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9002. Min Act: -0.1700
Data Index: 6283641 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9002. Min Act: -0.1700
Data Index: 6268185 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9002. Min Act: -0.1700
Data Index: 1584709 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9002. Min Act: -0.1700
Data Index: 554409 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.9002. Min Act: -0.1700
Data Index: 4963073 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.8690. Min Act: -0.1700
Data Index: 5238846 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7127. Min Range: -8.7127
Max Act: 7.8377. Min Act: -0.1700
Data Index: 7358970 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19