Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.7392. Min Act: -0.1700
Data Index: 7732086 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.3954. Min Act: -0.1700
Data Index: 4697392 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.3017. Min Act: -0.1700
Data Index: 6703431 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.3017. Min Act: -0.1700
Data Index: 7253712 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.2704. Min Act: -0.1700
Data Index: 5433481 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.2079. Min Act: -0.1700
Data Index: 3289868 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.1767. Min Act: -0.1700
Data Index: 2647532 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.1454. Min Act: -0.1700
Data Index: 1074078 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.1142. Min Act: -0.1700
Data Index: 7154636 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.1142. Min Act: -0.1700
Data Index: 5600330 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0829. Min Act: -0.1700
Data Index: 496310 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.1142. Min Act: -0.1700
Data Index: 8096176 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0517. Min Act: -0.1700
Data Index: 8607329 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0829. Min Act: -0.1700
Data Index: 5798218 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0829. Min Act: -0.1700
Data Index: 1558511 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0829. Min Act: -0.1700
Data Index: 8634560 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0517. Min Act: -0.1700
Data Index: 7633374 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0517. Min Act: -0.1700
Data Index: 4310236 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0204. Min Act: -0.1700
Data Index: 4047867 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7392. Min Range: -6.7392
Max Act: 6.0204. Min Act: -0.1700
Data Index: 3356498 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19