Model: None
Dataset: The Pile
Neuron 1137 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.7403. Min Act: -0.1700
Data Index: 4507768 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.6153. Min Act: -0.1700
Data Index: 4208916 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5840. Min Act: -0.1700
Data Index: 2906464 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5840. Min Act: -0.1700
Data Index: 9611492 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5528. Min Act: -0.1700
Data Index: 2621481 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5528. Min Act: -0.1700
Data Index: 4833740 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5528. Min Act: -0.1700
Data Index: 4852376 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5528. Min Act: -0.1700
Data Index: 179161 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5215. Min Act: -0.1700
Data Index: 10543458 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5215. Min Act: -0.1700
Data Index: 5926894 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5215. Min Act: -0.1700
Data Index: 9908251 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5215. Min Act: -0.1700
Data Index: 2140514 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5215. Min Act: -0.1700
Data Index: 8778040 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.5215. Min Act: -0.1700
Data Index: 4766185 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.4903. Min Act: -0.1700
Data Index: 2978376 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.4903. Min Act: -0.1700
Data Index: 4704083 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.4903. Min Act: -0.1700
Data Index: 4869081 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.4903. Min Act: -0.1700
Data Index: 4947208 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.4903. Min Act: -0.1700
Data Index: 6127481 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7403. Min Range: -4.7403
Max Act: 4.4903. Min Act: -0.1700
Data Index: 1017547 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19