Model: None
Dataset: The Pile
Neuron 2660 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2751. Min Act: -0.1700
Data Index: 10516355 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.0389. Min Act: -0.1700
Data Index: 3641325 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.0389. Min Act: -0.1700
Data Index: 1741026 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.0231. Min Act: -0.1700
Data Index: 7148362 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9915. Min Act: -0.1700
Data Index: 1075727 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9757. Min Act: -0.1700
Data Index: 2339758 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9599. Min Act: -0.1700
Data Index: 10267686 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9599. Min Act: -0.1700
Data Index: 7441691 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9599. Min Act: -0.1700
Data Index: 9336599 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9599. Min Act: -0.1700
Data Index: 2318536 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9599. Min Act: -0.1700
Data Index: 9080786 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9599. Min Act: -0.1700
Data Index: 4025103 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9440. Min Act: -0.1700
Data Index: 3174851 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9282. Min Act: -0.1700
Data Index: 1394422 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9282. Min Act: -0.1700
Data Index: 2426974 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9282. Min Act: -0.1700
Data Index: 4560769 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9282. Min Act: -0.1700
Data Index: 9578525 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.9123. Min Act: -0.1700
Data Index: 4994053 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.8965. Min Act: -0.1700
Data Index: 4700063 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2751. Min Range: -3.2751
Max Act: 2.8965. Min Act: -0.1700
Data Index: 2759749 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19