Model: None
Dataset: The Pile
Neuron 1792 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.6057. Min Act: -0.1700
Data Index: 860793 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.5744. Min Act: -0.1700
Data Index: 7792760 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3706. Min Act: -0.1700
Data Index: 4012383 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3706. Min Act: -0.1700
Data Index: 2190901 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3863. Min Act: -0.1700
Data Index: 8416605 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3549. Min Act: -0.1700
Data Index: 2649912 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3863. Min Act: -0.1700
Data Index: 694350 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3549. Min Act: -0.1700
Data Index: 8335138 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3706. Min Act: -0.1700
Data Index: 7583357 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3235. Min Act: -0.1700
Data Index: 1609409 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3235. Min Act: -0.1700
Data Index: 9809216 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3392. Min Act: -0.1700
Data Index: 5039192 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3235. Min Act: -0.1700
Data Index: 8916601 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.2921. Min Act: -0.1700
Data Index: 6861308 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3235. Min Act: -0.1700
Data Index: 9776038 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.2764. Min Act: -0.1700
Data Index: 2182887 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.3078. Min Act: -0.1700
Data Index: 775160 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.2921. Min Act: -0.1700
Data Index: 6827825 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.2764. Min Act: -0.1700
Data Index: 8324581 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6057. Min Range: -3.6057
Max Act: 3.2921. Min Act: -0.1700
Data Index: 3020101 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19