Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2031. Min Range: -8.2031
Max Act: 8.2031. Min Act: -0.1700
Data Index: 7142949 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.6406. Min Act: -0.1700
Data Index: 7857507 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.2344. Min Act: -0.1700
Data Index: 1667864 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.2031. Min Act: -0.1700
Data Index: 270783 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.1719. Min Act: -0.1700
Data Index: 3563335 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.1094. Min Act: -0.1700
Data Index: 4236501 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.1094. Min Act: -0.1700
Data Index: 6195195 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.0781. Min Act: -0.1700
Data Index: 1515879 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.0469. Min Act: -0.1700
Data Index: 3079000 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.0469. Min Act: -0.1700
Data Index: 6938077 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2031. Min Range: -8.2031
Max Act: 7.0156. Min Act: -0.1700
Data Index: 6235968 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.9844. Min Act: -0.1700
Data Index: 8482472 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.9844. Min Act: -0.1700
Data Index: 70573 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.9844. Min Act: -0.1700
Data Index: 4453332 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.9531. Min Act: -0.1700
Data Index: 2570880 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.9531. Min Act: -0.1700
Data Index: 2409737 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.8906. Min Act: -0.1700
Data Index: 3435939 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.8906. Min Act: -0.1700
Data Index: 7833535 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.8906. Min Act: -0.1700
Data Index: 5317977 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2031. Min Range: -8.2031
Max Act: 6.8906. Min Act: -0.1700
Data Index: 5872047 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19