Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3753 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0949. Min Range: -8.0949
Max Act: 8.0949. Min Act: -0.1700
Data Index: 83743 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.9699. Min Act: -0.1700
Data Index: 7338871 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.9699. Min Act: -0.1700
Data Index: 2496293 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.9074. Min Act: -0.1700
Data Index: 4377670 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.8449. Min Act: -0.1700
Data Index: 6674605 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.7824. Min Act: -0.1700
Data Index: 7094720 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.7824. Min Act: -0.1700
Data Index: 2037163 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.7824. Min Act: -0.1700
Data Index: 408086 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.7199. Min Act: -0.1700
Data Index: 7347959 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.6574. Min Act: -0.1700
Data Index: 5071104 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.7199. Min Act: -0.1700
Data Index: 3392729 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.6574. Min Act: -0.1700
Data Index: 6311843 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.6574. Min Act: -0.1700
Data Index: 5914457 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.6574. Min Act: -0.1700
Data Index: 3973731 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.5949. Min Act: -0.1700
Data Index: 6946411 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.5949. Min Act: -0.1700
Data Index: 5029431 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.5949. Min Act: -0.1700
Data Index: 7977081 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.5949. Min Act: -0.1700
Data Index: 8243269 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.5324. Min Act: -0.1700
Data Index: 6184587 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0949. Min Range: -8.0949
Max Act: 7.5949. Min Act: -0.1700
Data Index: 5388283 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19