Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1658. Min Act: -0.1700
Data Index: 8296552 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1186. Min Act: -0.1700
Data Index: 4992842 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1186. Min Act: -0.1700
Data Index: 2963154 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1186. Min Act: -0.1700
Data Index: 3713195 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0871. Min Act: -0.1700
Data Index: 1079318 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0871. Min Act: -0.1700
Data Index: 2804454 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0871. Min Act: -0.1700
Data Index: 532692 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0713. Min Act: -0.1700
Data Index: 7006930 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0713. Min Act: -0.1700
Data Index: 8461484 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0713. Min Act: -0.1700
Data Index: 5445946 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0713. Min Act: -0.1700
Data Index: 550344 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0713. Min Act: -0.1700
Data Index: 3713199 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 8558675 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 3934090 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 2993928 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 1980669 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 1712283 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 7222659 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 611157 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 7086247 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19