Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5924 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.3207. Min Act: -0.1700
Data Index: 6614441 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.1644. Min Act: -0.1700
Data Index: 3357494 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.0394. Min Act: -0.1700
Data Index: 4165753 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.0394. Min Act: -0.1700
Data Index: 3357493 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.0081. Min Act: -0.1700
Data Index: 375491 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.0081. Min Act: -0.1700
Data Index: 7995402 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3207. Min Range: -4.3207
Max Act: 4.0081. Min Act: -0.1700
Data Index: 2796027 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9769. Min Act: -0.1700
Data Index: 5182585 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9769. Min Act: -0.1700
Data Index: 3357492 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9456. Min Act: -0.1700
Data Index: 7694629 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9456. Min Act: -0.1700
Data Index: 8002397 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 4059157 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 7409054 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 73999 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.8831. Min Act: -0.1700
Data Index: 5354860 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 5438893 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 6632155 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 4263842 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9456. Min Act: -0.1700
Data Index: 8104715 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3207. Min Range: -4.3207
Max Act: 3.9144. Min Act: -0.1700
Data Index: 5303901 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19