Model: None
Dataset: The Pile
Neuron 333 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.8136. Min Act: -0.1700
Data Index: 10649014 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.8136. Min Act: -0.1700
Data Index: 6373810 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7980. Min Act: -0.1700
Data Index: 1996532 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7980. Min Act: -0.1700
Data Index: 2502313 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7667. Min Act: -0.1700
Data Index: 7677273 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7511. Min Act: -0.1700
Data Index: 2567906 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7354. Min Act: -0.1700
Data Index: 8392628 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7511. Min Act: -0.1700
Data Index: 431913 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7041. Min Act: -0.1700
Data Index: 6729327 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7198. Min Act: -0.1700
Data Index: 6530081 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7198. Min Act: -0.1700
Data Index: 1651153 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7198. Min Act: -0.1700
Data Index: 479008 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.6728. Min Act: -0.1700
Data Index: 3969022 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7041. Min Act: -0.1700
Data Index: 343388 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7198. Min Act: -0.1700
Data Index: 1265060 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7198. Min Act: -0.1700
Data Index: 2121401 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7041. Min Act: -0.1700
Data Index: 2039270 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7041. Min Act: -0.1700
Data Index: 7260001 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7198. Min Act: -0.1700
Data Index: 1562255 (The Pile)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8136. Min Range: -3.8136
Max Act: 3.7041. Min Act: -0.1700
Data Index: 3483543 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19