Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.6260. Min Act: -0.1700
Data Index: 8577076 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.6260. Min Act: -0.1700
Data Index: 6121485 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5948. Min Act: -0.1700
Data Index: 647924 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5948. Min Act: -0.1700
Data Index: 5448868 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5948. Min Act: -0.1700
Data Index: 5569515 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5948. Min Act: -0.1700
Data Index: 2185662 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5948. Min Act: -0.1700
Data Index: 492289 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5635. Min Act: -0.1700
Data Index: 4606112 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6488916 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5635. Min Act: -0.1700
Data Index: 6436441 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5635. Min Act: -0.1700
Data Index: 421603 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5635. Min Act: -0.1700
Data Index: 5718025 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6203212 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5010. Min Act: -0.1700
Data Index: 4061004 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5635. Min Act: -0.1700
Data Index: 4019425 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6707022 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 5916977 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 8232553 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 3695180 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6260. Min Range: -5.6260
Max Act: 5.5010. Min Act: -0.1700
Data Index: 7408709 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19