Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.4102. Min Act: -0.1700
Data Index: 3071390 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.3474. Min Act: -0.1700
Data Index: 4256824 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.2061. Min Act: -0.1700
Data Index: 7625292 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.2061. Min Act: -0.1700
Data Index: 769324 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.1432. Min Act: -0.1700
Data Index: 4325916 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.1432. Min Act: -0.1700
Data Index: 1419040 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.1432. Min Act: -0.1700
Data Index: 8212474 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.1589. Min Act: -0.1700
Data Index: 4658505 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.1274. Min Act: -0.1700
Data Index: 1334476 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.1274. Min Act: -0.1700
Data Index: 4593837 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0959. Min Act: -0.1700
Data Index: 4213807 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0959. Min Act: -0.1700
Data Index: 3282856 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0959. Min Act: -0.1700
Data Index: 7505601 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0486. Min Act: -0.1700
Data Index: 3170589 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0486. Min Act: -0.1700
Data Index: 3839356 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0644. Min Act: -0.1700
Data Index: 3282855 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0644. Min Act: -0.1700
Data Index: 6585632 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0801. Min Act: -0.1700
Data Index: 8119533 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0644. Min Act: -0.1700
Data Index: 5792469 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4102. Min Range: -3.4102
Max Act: 3.0486. Min Act: -0.1700
Data Index: 5625605 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19