Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0916. Min Act: -0.1700
Data Index: 5043039 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0291. Min Act: -0.1700
Data Index: 6952844 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9666. Min Act: -0.1700
Data Index: 4283128 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8416. Min Act: -0.1700
Data Index: 1179104 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7478. Min Act: -0.1700
Data Index: 6825036 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7791. Min Act: -0.1700
Data Index: 1235659 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7791. Min Act: -0.1700
Data Index: 2394319 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7166. Min Act: -0.1700
Data Index: 5626129 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7166. Min Act: -0.1700
Data Index: 3829330 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7478. Min Act: -0.1700
Data Index: 8273986 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7478. Min Act: -0.1700
Data Index: 3153429 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7478. Min Act: -0.1700
Data Index: 3497679 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.7166. Min Act: -0.1700
Data Index: 3685601 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 1235660 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 6454850 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 5866792 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 2750067 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 1574085 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 2088129 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.6853. Min Act: -0.1700
Data Index: 8494127 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19