Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.2071. Min Act: -0.1700
Data Index: 76225 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1126. Min Act: -0.1700
Data Index: 4063761 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1126. Min Act: -0.1700
Data Index: 163251 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0969. Min Act: -0.1700
Data Index: 3795321 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1126. Min Act: -0.1700
Data Index: 6792089 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1126. Min Act: -0.1700
Data Index: 7172412 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1126. Min Act: -0.1700
Data Index: 6690204 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0969. Min Act: -0.1700
Data Index: 4063762 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0811. Min Act: -0.1700
Data Index: 4925760 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0653. Min Act: -0.1700
Data Index: 1623214 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0811. Min Act: -0.1700
Data Index: 2993888 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 2875369 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 6304557 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 291575 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0811. Min Act: -0.1700
Data Index: 6098378 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 4149036 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0180. Min Act: -0.1700
Data Index: 2759409 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0180. Min Act: -0.1700
Data Index: 5015181 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0338. Min Act: -0.1700
Data Index: 5198557 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0338. Min Act: -0.1700
Data Index: 2759408 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19