Model: None
Dataset: The Pile
Neuron 822 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.8475. Min Act: -0.1700
Data Index: 3045783 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.7537. Min Act: -0.1700
Data Index: 3572819 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.7225. Min Act: -0.1700
Data Index: 4628031 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6912. Min Act: -0.1700
Data Index: 7234715 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6912. Min Act: -0.1700
Data Index: 3517569 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6912. Min Act: -0.1700
Data Index: 9303108 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6912. Min Act: -0.1700
Data Index: 6911472 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6912. Min Act: -0.1700
Data Index: 1091629 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6600. Min Act: -0.1700
Data Index: 6566226 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6600. Min Act: -0.1700
Data Index: 9917055 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6600. Min Act: -0.1700
Data Index: 4324170 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6287. Min Act: -0.1700
Data Index: 8781244 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6287. Min Act: -0.1700
Data Index: 6378442 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.6287. Min Act: -0.1700
Data Index: 4472623 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.5975. Min Act: -0.1700
Data Index: 3242985 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.5975. Min Act: -0.1700
Data Index: 3634517 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.5975. Min Act: -0.1700
Data Index: 8605930 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.5975. Min Act: -0.1700
Data Index: 6199702 (The Pile)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.5662. Min Act: -0.1700
Data Index: 6442725 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8475. Min Range: -4.8475
Max Act: 4.5662. Min Act: -0.1700
Data Index: 1221241 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19