Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0967. Min Range: -6.0967
Max Act: 6.0967. Min Act: -0.1700
Data Index: 6927960 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0967. Min Range: -6.0967
Max Act: 6.0654. Min Act: -0.1700
Data Index: 6142049 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0967. Min Range: -6.0967
Max Act: 6.0029. Min Act: -0.1700
Data Index: 1033897 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9404. Min Act: -0.1700
Data Index: 3740674 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9404. Min Act: -0.1700
Data Index: 3240938 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9404. Min Act: -0.1700
Data Index: 5620612 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9092. Min Act: -0.1700
Data Index: 1033900 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9092. Min Act: -0.1700
Data Index: 4430463 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8779. Min Act: -0.1700
Data Index: 5029158 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8779. Min Act: -0.1700
Data Index: 6093843 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8779. Min Act: -0.1700
Data Index: 6036522 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8779. Min Act: -0.1700
Data Index: 5853065 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8779. Min Act: -0.1700
Data Index: 855737 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8467. Min Act: -0.1700
Data Index: 1033898 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8154. Min Act: -0.1700
Data Index: 7142332 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7842. Min Act: -0.1700
Data Index: 4035854 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7529. Min Act: -0.1700
Data Index: 2780521 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7842. Min Act: -0.1700
Data Index: 1687781 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7842. Min Act: -0.1700
Data Index: 526685 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7529. Min Act: -0.1700
Data Index: 4532386 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19