Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.6813. Min Act: -0.1700
Data Index: 5045241 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.6500. Min Act: -0.1700
Data Index: 6685700 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.5875. Min Act: -0.1700
Data Index: 3380190 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.5250. Min Act: -0.1700
Data Index: 2929490 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.4625. Min Act: -0.1700
Data Index: 8348529 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.4000. Min Act: -0.1700
Data Index: 8120195 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 8328558 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.3688. Min Act: -0.1700
Data Index: 4899034 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.3063. Min Act: -0.1700
Data Index: 5967999 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.3063. Min Act: -0.1700
Data Index: 7302114 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.3375. Min Act: -0.1700
Data Index: 2936609 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.3063. Min Act: -0.1700
Data Index: 4899031 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.2438. Min Act: -0.1700
Data Index: 5713860 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.2125. Min Act: -0.1700
Data Index: 5178444 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.1813. Min Act: -0.1700
Data Index: 8117488 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.1500. Min Act: -0.1700
Data Index: 7714203 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.1500. Min Act: -0.1700
Data Index: 8117489 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.1188. Min Act: -0.1700
Data Index: 495453 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.1188. Min Act: -0.1700
Data Index: 2296893 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6813. Min Range: -6.6813
Max Act: 6.1500. Min Act: -0.1700
Data Index: 1609100 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19