Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1430. Min Range: -9.1430
Max Act: 9.1430. Min Act: -0.1700
Data Index: 1325030 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.6430. Min Act: -0.1700
Data Index: 5307531 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.3930. Min Act: -0.1700
Data Index: 4723441 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.3930. Min Act: -0.1700
Data Index: 1498510 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.3305. Min Act: -0.1700
Data Index: 1544142 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.2680. Min Act: -0.1700
Data Index: 880250 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.2680. Min Act: -0.1700
Data Index: 4058517 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.1742. Min Act: -0.1700
Data Index: 4928462 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.1742. Min Act: -0.1700
Data Index: 5580837 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.1430. Min Act: -0.1700
Data Index: 441783 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.1117. Min Act: -0.1700
Data Index: 1470463 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.1117. Min Act: -0.1700
Data Index: 4973456 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.1117. Min Act: -0.1700
Data Index: 5736187 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.0805. Min Act: -0.1700
Data Index: 3334902 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.0492. Min Act: -0.1700
Data Index: 5862530 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.0492. Min Act: -0.1700
Data Index: 407590 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.0180. Min Act: -0.1700
Data Index: 2856579 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1430. Min Range: -9.1430
Max Act: 8.0180. Min Act: -0.1700
Data Index: 3378828 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1430. Min Range: -9.1430
Max Act: 7.9867. Min Act: -0.1700
Data Index: 3658776 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1430. Min Range: -9.1430
Max Act: 7.9555. Min Act: -0.1700
Data Index: 2333273 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19