Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3760 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.6800. Min Act: -0.1700
Data Index: 644649 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.5550. Min Act: -0.1700
Data Index: 7495694 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.5550. Min Act: -0.1700
Data Index: 6964563 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.5550. Min Act: -0.1700
Data Index: 3712467 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.5237. Min Act: -0.1700
Data Index: 674339 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.4612. Min Act: -0.1700
Data Index: 8072570 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.4612. Min Act: -0.1700
Data Index: 6964562 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.4612. Min Act: -0.1700
Data Index: 8387402 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.4612. Min Act: -0.1700
Data Index: 4956494 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.4612. Min Act: -0.1700
Data Index: 6257147 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.4300. Min Act: -0.1700
Data Index: 1541517 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3675. Min Act: -0.1700
Data Index: 2345599 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3987. Min Act: -0.1700
Data Index: 120487 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3987. Min Act: -0.1700
Data Index: 2345602 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3987. Min Act: -0.1700
Data Index: 4151461 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3987. Min Act: -0.1700
Data Index: 5083653 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3987. Min Act: -0.1700
Data Index: 4410107 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3987. Min Act: -0.1700
Data Index: 7818897 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3675. Min Act: -0.1700
Data Index: 2818061 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6800. Min Range: -6.6800
Max Act: 6.3675. Min Act: -0.1700
Data Index: 149007 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19