Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2503. Min Range: -5.2503
Max Act: 5.2503. Min Act: -0.1700
Data Index: 1004727 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2503. Min Range: -5.2503
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4236414 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2503. Min Range: -5.2503
Max Act: 5.0003. Min Act: -0.1700
Data Index: 2781320 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9690. Min Act: -0.1700
Data Index: 8740468 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9690. Min Act: -0.1700
Data Index: 6037817 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9690. Min Act: -0.1700
Data Index: 1004728 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9065. Min Act: -0.1700
Data Index: 4978266 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9378. Min Act: -0.1700
Data Index: 1194404 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9378. Min Act: -0.1700
Data Index: 4118788 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9065. Min Act: -0.1700
Data Index: 3456405 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.9065. Min Act: -0.1700
Data Index: 5852475 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8753. Min Act: -0.1700
Data Index: 613929 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8753. Min Act: -0.1700
Data Index: 6925544 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8753. Min Act: -0.1700
Data Index: 8334212 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8440. Min Act: -0.1700
Data Index: 2068663 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8440. Min Act: -0.1700
Data Index: 4874551 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8440. Min Act: -0.1700
Data Index: 8482426 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8440. Min Act: -0.1700
Data Index: 3705889 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8440. Min Act: -0.1700
Data Index: 2476249 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2503. Min Range: -5.2503
Max Act: 4.8440. Min Act: -0.1700
Data Index: 980423 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19