Model: None
Dataset: The Pile
Neuron 324 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.8170. Min Act: -0.1700
Data Index: 5411306 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.8011. Min Act: -0.1700
Data Index: 7861312 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.7373. Min Act: -0.1700
Data Index: 1365949 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6893. Min Act: -0.1700
Data Index: 4062681 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6733. Min Act: -0.1700
Data Index: 7676720 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6573. Min Act: -0.1700
Data Index: 4999262 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6573. Min Act: -0.1700
Data Index: 10307353 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6573. Min Act: -0.1700
Data Index: 10638746 (The Pile)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6091. Min Act: -0.1700
Data Index: 3526375 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.6091. Min Act: -0.1700
Data Index: 8054387 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5930. Min Act: -0.1700
Data Index: 8368993 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5930. Min Act: -0.1700
Data Index: 9479764 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5930. Min Act: -0.1700
Data Index: 4668788 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5930. Min Act: -0.1700
Data Index: 3628575 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5930. Min Act: -0.1700
Data Index: 3148858 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5930. Min Act: -0.1700
Data Index: 3754679 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5769. Min Act: -0.1700
Data Index: 76142 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5769. Min Act: -0.1700
Data Index: 5770448 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5769. Min Act: -0.1700
Data Index: 709641 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8170. Min Range: -2.8170
Max Act: 2.5769. Min Act: -0.1700
Data Index: 7280714 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19