Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5565 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.6503. Min Act: -0.1700
Data Index: 5071211 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.5878. Min Act: -0.1700
Data Index: 1023278 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.4628. Min Act: -0.1700
Data Index: 777415 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.4628. Min Act: -0.1700
Data Index: 7113816 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.4003. Min Act: -0.1700
Data Index: 6056058 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.4003. Min Act: -0.1700
Data Index: 6394471 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.3691. Min Act: -0.1700
Data Index: 7333023 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.3378. Min Act: -0.1700
Data Index: 4715132 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.3378. Min Act: -0.1700
Data Index: 4478131 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.3378. Min Act: -0.1700
Data Index: 2778934 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.3378. Min Act: -0.1700
Data Index: 7982816 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.3066. Min Act: -0.1700
Data Index: 3791062 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2753. Min Act: -0.1700
Data Index: 7270273 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2753. Min Act: -0.1700
Data Index: 2141427 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2753. Min Act: -0.1700
Data Index: 2125551 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2753. Min Act: -0.1700
Data Index: 3419388 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2753. Min Act: -0.1700
Data Index: 8166073 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2441. Min Act: -0.1700
Data Index: 7075120 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2441. Min Act: -0.1700
Data Index: 4089747 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6503. Min Range: -5.6503
Max Act: 5.2128. Min Act: -0.1700
Data Index: 8590346 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19