Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6749. Min Act: -0.1700
Data Index: 8826236 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.7062. Min Act: -0.1700
Data Index: 2603066 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6749. Min Act: -0.1700
Data Index: 1803488 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6749. Min Act: -0.1700
Data Index: 2264938 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6749. Min Act: -0.1700
Data Index: 5203218 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.7062. Min Act: -0.1700
Data Index: 8301542 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6749. Min Act: -0.1700
Data Index: 1502252 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6436. Min Act: -0.1700
Data Index: 3796910 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6436. Min Act: -0.1700
Data Index: 5756210 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6436. Min Act: -0.1700
Data Index: 1858089 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1693
Data Index: 3200604 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1700
Data Index: 8259531 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1700
Data Index: 3046290 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1700
Data Index: 6887212 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1700
Data Index: 6125152 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1700
Data Index: 5240466 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.6123. Min Act: -0.1700
Data Index: 4731111 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.5810. Min Act: -0.1700
Data Index: 3213860 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.5810. Min Act: -0.1700
Data Index: 3500102 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7062. Min Range: -3.7062
Max Act: 3.5810. Min Act: -0.1700
Data Index: 975855 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19