Model: None
Dataset: The Pile
Neuron 824 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.7186. Min Act: -0.1700
Data Index: 5750037 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.6385. Min Act: -0.1700
Data Index: 5694462 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.6225. Min Act: -0.1700
Data Index: 1797880 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5903. Min Act: -0.1700
Data Index: 7718162 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5903. Min Act: -0.1700
Data Index: 5101274 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5903. Min Act: -0.1700
Data Index: 1322627 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5742. Min Act: -0.1700
Data Index: 2627381 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5581. Min Act: -0.1700
Data Index: 8755124 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5581. Min Act: -0.1700
Data Index: 10613944 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5581. Min Act: -0.1700
Data Index: 3578387 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5581. Min Act: -0.1700
Data Index: 901805 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5581. Min Act: -0.1700
Data Index: 4643932 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5419. Min Act: -0.1700
Data Index: 3016906 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5419. Min Act: -0.1700
Data Index: 7887730 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5419. Min Act: -0.1700
Data Index: 6531467 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5419. Min Act: -0.1700
Data Index: 9172447 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5419. Min Act: -0.1700
Data Index: 9367594 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5258. Min Act: -0.1700
Data Index: 881775 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5258. Min Act: -0.1698
Data Index: 1003601 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7186. Min Range: -2.7186
Max Act: 2.5258. Min Act: -0.1700
Data Index: 554849 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19