Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1142 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2873. Min Range: -9.2873
Max Act: 9.2873. Min Act: -0.1700
Data Index: 3511799 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2873. Min Range: -9.2873
Max Act: 9.1623. Min Act: -0.1700
Data Index: 7271518 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2873. Min Range: -9.2873
Max Act: 9.0373. Min Act: -0.1700
Data Index: 8354959 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.9748. Min Act: -0.1700
Data Index: 3017036 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.9123. Min Act: -0.1700
Data Index: 4413853 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7873. Min Act: -0.1700
Data Index: 3210083 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7873. Min Act: -0.1700
Data Index: 5772302 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.8498. Min Act: -0.1700
Data Index: 8780603 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7873. Min Act: -0.1700
Data Index: 5248189 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7873. Min Act: -0.1700
Data Index: 2033164 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7873. Min Act: -0.1700
Data Index: 8715368 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7248. Min Act: -0.1700
Data Index: 4740848 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7248. Min Act: -0.1700
Data Index: 8777082 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.7248. Min Act: -0.1700
Data Index: 6239221 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.6623. Min Act: -0.1700
Data Index: 2254181 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.6623. Min Act: -0.1700
Data Index: 1124733 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.6623. Min Act: -0.1700
Data Index: 4006226 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.6623. Min Act: -0.1700
Data Index: 8240330 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.6623. Min Act: -0.1700
Data Index: 3773880 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2873. Min Range: -9.2873
Max Act: 8.5998. Min Act: -0.1700
Data Index: 4974650 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19