Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.8813. Min Act: -0.1700
Data Index: 6500308 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.8031. Min Act: -0.1700
Data Index: 6012368 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.6624. Min Act: -0.1700
Data Index: 1742995 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.6467. Min Act: -0.1700
Data Index: 4696170 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.6311. Min Act: -0.1700
Data Index: 2580306 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.6154. Min Act: -0.1700
Data Index: 7217924 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5998. Min Act: -0.1700
Data Index: 6860057 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5998. Min Act: -0.1700
Data Index: 5682352 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5841. Min Act: -0.1700
Data Index: 1425819 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5841. Min Act: -0.1700
Data Index: 4929377 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5685. Min Act: -0.1700
Data Index: 4317438 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5372. Min Act: -0.1700
Data Index: 1916772 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5372. Min Act: -0.1700
Data Index: 1095619 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5528. Min Act: -0.1700
Data Index: 1593366 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5528. Min Act: -0.1700
Data Index: 5504565 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5215. Min Act: -0.1700
Data Index: 7319399 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5528. Min Act: -0.1700
Data Index: 2622367 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5215. Min Act: -0.1700
Data Index: 1846937 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5372. Min Act: -0.1700
Data Index: 6519459 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8813. Min Range: -3.8813
Max Act: 3.5058. Min Act: -0.1700
Data Index: 285354 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19