Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0076. Min Range: -7.0076
Max Act: 7.0076. Min Act: -0.1700
Data Index: 5689650 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6951. Min Act: -0.1700
Data Index: 3541901 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6326. Min Act: -0.1700
Data Index: 7928734 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6013. Min Act: -0.1700
Data Index: 6445511 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6013. Min Act: -0.1700
Data Index: 3587198 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6013. Min Act: -0.1700
Data Index: 1103227 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6013. Min Act: -0.1700
Data Index: 6548066 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6013. Min Act: -0.1700
Data Index: 2255625 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5701. Min Act: -0.1700
Data Index: 8640392 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.6013. Min Act: -0.1700
Data Index: 3208127 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5701. Min Act: -0.1700
Data Index: 8015237 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5701. Min Act: -0.1700
Data Index: 5989353 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5701. Min Act: -0.1700
Data Index: 7184292 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5701. Min Act: -0.1700
Data Index: 1174195 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5388. Min Act: -0.1700
Data Index: 4814981 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5076. Min Act: -0.1700
Data Index: 6116814 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5076. Min Act: -0.1700
Data Index: 5608930 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.5076. Min Act: -0.1700
Data Index: 4805134 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.4763. Min Act: -0.1700
Data Index: 2850396 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0076. Min Range: -7.0076
Max Act: 6.4763. Min Act: -0.1700
Data Index: 5437431 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19