Model: None
Dataset: The Pile
Neuron 3037 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.0436. Min Range: -4.0436
Max Act: 4.0436. Min Act: -0.1700
Data Index: 4286550 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.9655. Min Act: -0.1700
Data Index: 2033267 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.9498. Min Act: -0.1700
Data Index: 122881 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.9186. Min Act: -0.1700
Data Index: 2553196 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.8560. Min Act: -0.1700
Data Index: 4594410 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.8404. Min Act: -0.1700
Data Index: 310125 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.8404. Min Act: -0.1700
Data Index: 10347256 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7778. Min Act: -0.1700
Data Index: 2329762 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7622. Min Act: -0.1700
Data Index: 2517676 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7622. Min Act: -0.1700
Data Index: 3673257 (The Pile)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7465. Min Act: -0.1700
Data Index: 9444189 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7465. Min Act: -0.1700
Data Index: 3964159 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7465. Min Act: -0.1700
Data Index: 3224312 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7309. Min Act: -0.1700
Data Index: 783396 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7309. Min Act: -0.1700
Data Index: 10548041 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7152. Min Act: -0.1700
Data Index: 1180660 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7152. Min Act: -0.1700
Data Index: 1232966 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.7152. Min Act: -0.1700
Data Index: 693713 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.6996. Min Act: -0.1700
Data Index: 3213352 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0436. Min Range: -4.0436
Max Act: 3.6996. Min Act: -0.1700
Data Index: 5153547 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19