Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2468 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1084. Min Range: -6.1084
Max Act: 6.1084. Min Act: -0.1700
Data Index: 7171239 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.9834. Min Act: -0.1700
Data Index: 1838639 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.9522. Min Act: -0.1700
Data Index: 7382088 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.8897. Min Act: -0.1700
Data Index: 4367528 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.7959. Min Act: -0.1700
Data Index: 2895116 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1838641 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.7334. Min Act: -0.1700
Data Index: 4259973 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.7022. Min Act: -0.1700
Data Index: 3459933 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.6397. Min Act: -0.1700
Data Index: 3220 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.6709. Min Act: -0.1700
Data Index: 7848527 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.6397. Min Act: -0.1700
Data Index: 2931007 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.6084. Min Act: -0.1700
Data Index: 399543 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.6084. Min Act: -0.1700
Data Index: 2067630 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5772. Min Act: -0.1700
Data Index: 75254 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5772. Min Act: -0.1700
Data Index: 1727396 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5772. Min Act: -0.1700
Data Index: 7162892 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5772. Min Act: -0.1700
Data Index: 651024 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5772. Min Act: -0.1700
Data Index: 3314475 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5772. Min Act: -0.1700
Data Index: 8611523 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1084. Min Range: -6.1084
Max Act: 5.5459. Min Act: -0.1700
Data Index: 3429520 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19