Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 224 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.8841. Min Act: -0.1700
Data Index: 3110037 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.8528. Min Act: -0.1700
Data Index: 1198501 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.7591. Min Act: -0.1700
Data Index: 499418 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6966. Min Act: -0.1700
Data Index: 3144806 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6653. Min Act: -0.1700
Data Index: 2641972 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6653. Min Act: -0.1700
Data Index: 8246742 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6653. Min Act: -0.1700
Data Index: 4729183 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6341. Min Act: -0.1700
Data Index: 5756546 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6341. Min Act: -0.1700
Data Index: 7217105 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6341. Min Act: -0.1700
Data Index: 2299673 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6341. Min Act: -0.1700
Data Index: 6084059 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 2119570 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6341. Min Act: -0.1700
Data Index: 4366267 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 8041878 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 5169041 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6341. Min Act: -0.1700
Data Index: 6057527 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 1951117 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 8553340 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 499424 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8841. Min Range: -5.8841
Max Act: 5.6028. Min Act: -0.1700
Data Index: 3409202 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19