Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1727 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1150. Min Range: -4.1150
Max Act: 4.1150. Min Act: -0.1700
Data Index: 8474216 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1150. Min Range: -4.1150
Max Act: 4.0212. Min Act: -0.1700
Data Index: 3672664 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1150. Min Range: -4.1150
Max Act: 4.0212. Min Act: -0.1700
Data Index: 5813148 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1150. Min Range: -4.1150
Max Act: 4.0525. Min Act: -0.1700
Data Index: 1959733 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.9899. Min Act: -0.1700
Data Index: 4071455 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.9899. Min Act: -0.1700
Data Index: 6535588 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.9587. Min Act: -0.1700
Data Index: 618976 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.9431. Min Act: -0.1700
Data Index: 7721509 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.9118. Min Act: -0.1700
Data Index: 2149140 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.9274. Min Act: -0.1700
Data Index: 859372 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8962. Min Act: -0.1700
Data Index: 4396237 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8805. Min Act: -0.1700
Data Index: 6653755 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8649. Min Act: -0.1700
Data Index: 7911145 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8493. Min Act: -0.1700
Data Index: 5178425 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8493. Min Act: -0.1700
Data Index: 8052027 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8336. Min Act: -0.1700
Data Index: 5956447 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8493. Min Act: -0.1700
Data Index: 7052614 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8493. Min Act: -0.1700
Data Index: 4511424 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8336. Min Act: -0.1700
Data Index: 7452254 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1150. Min Range: -4.1150
Max Act: 3.8336. Min Act: -0.1700
Data Index: 620543 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19