Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.4014. Min Act: -0.1700
Data Index: 3134442 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.4014. Min Act: -0.1700
Data Index: 7752263 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.2451. Min Act: -0.1700
Data Index: 5456277 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.1514. Min Act: -0.1700
Data Index: 7597902 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.1514. Min Act: -0.1700
Data Index: 8009354 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.1514. Min Act: -0.1700
Data Index: 4576403 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.1201. Min Act: -0.1700
Data Index: 5736958 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4014. Min Range: -7.4014
Max Act: 7.0889. Min Act: -0.1700
Data Index: 5581524 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.9951. Min Act: -0.1700
Data Index: 6808241 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.9639. Min Act: -0.1700
Data Index: 3061126 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.9326. Min Act: -0.1700
Data Index: 463041 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.9014. Min Act: -0.1700
Data Index: 2483339 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.9326. Min Act: -0.1700
Data Index: 3935660 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.8389. Min Act: -0.1700
Data Index: 6741070 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.8701. Min Act: -0.1700
Data Index: 4741390 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.8701. Min Act: -0.1700
Data Index: 1253565 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.8076. Min Act: -0.1700
Data Index: 311356 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.8076. Min Act: -0.1700
Data Index: 3453966 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.8389. Min Act: -0.1700
Data Index: 3284617 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4014. Min Range: -7.4014
Max Act: 6.7764. Min Act: -0.1700
Data Index: 784518 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19