Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2445 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.8752. Min Act: -0.1700
Data Index: 103422 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.8440. Min Act: -0.1700
Data Index: 4977220 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.7190. Min Act: -0.1700
Data Index: 6438694 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6877. Min Act: -0.1700
Data Index: 8424729 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6565. Min Act: -0.1700
Data Index: 103424 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6565. Min Act: -0.1700
Data Index: 3765200 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6565. Min Act: -0.1700
Data Index: 1664407 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6565. Min Act: -0.1700
Data Index: 6781800 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6565. Min Act: -0.1700
Data Index: 1330459 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6252. Min Act: -0.1700
Data Index: 5450893 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6252. Min Act: -0.1700
Data Index: 3049484 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6252. Min Act: -0.1700
Data Index: 103429 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5940. Min Act: -0.1700
Data Index: 7345988 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5940. Min Act: -0.1700
Data Index: 1053339 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5627. Min Act: -0.1700
Data Index: 103420 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5940. Min Act: -0.1700
Data Index: 4403050 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5315. Min Act: -0.1700
Data Index: 6483787 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5627. Min Act: -0.1700
Data Index: 5953774 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5627. Min Act: -0.1700
Data Index: 4288286 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5627. Min Act: -0.1700
Data Index: 5953775 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19