Model: None
Dataset: The Pile
Neuron 2191 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.2509. Min Act: -0.1700
Data Index: 74228 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.2195. Min Act: -0.1700
Data Index: 10504083 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.2195. Min Act: -0.1700
Data Index: 5290549 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.2037. Min Act: -0.1700
Data Index: 3748761 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.2037. Min Act: -0.1700
Data Index: 1519013 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.2037. Min Act: -0.1700
Data Index: 5403359 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1880. Min Act: -0.1700
Data Index: 3174561 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1880. Min Act: -0.1700
Data Index: 3044147 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1880. Min Act: -0.1700
Data Index: 4057970 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1880. Min Act: -0.1700
Data Index: 8596721 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1723. Min Act: -0.1700
Data Index: 1962326 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1723. Min Act: -0.1700
Data Index: 293346 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1723. Min Act: -0.1700
Data Index: 6541953 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1723. Min Act: -0.1700
Data Index: 10506739 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1565. Min Act: -0.1700
Data Index: 4241496 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1565. Min Act: -0.1700
Data Index: 3822173 (The Pile)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1408. Min Act: -0.1700
Data Index: 6531809 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1408. Min Act: -0.1700
Data Index: 7625577 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1408. Min Act: -0.1700
Data Index: 3449871 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2509. Min Range: -3.2509
Max Act: 3.1250. Min Act: -0.1700
Data Index: 1594785 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19