Model: None
Dataset: The Pile
Neuron 570 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.8279. Min Act: -0.1700
Data Index: 4141467 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.8120. Min Act: -0.1700
Data Index: 492343 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7960. Min Act: -0.1700
Data Index: 3418955 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7801. Min Act: -0.1700
Data Index: 8518043 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7642. Min Act: -0.1700
Data Index: 7558903 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7642. Min Act: -0.1700
Data Index: 1044994 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7482. Min Act: -0.1700
Data Index: 10163306 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7482. Min Act: -0.1700
Data Index: 4495054 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7482. Min Act: -0.1700
Data Index: 4966132 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7322. Min Act: -0.1700
Data Index: 10706456 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7322. Min Act: -0.1700
Data Index: 8475912 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7322. Min Act: -0.1700
Data Index: 4092218 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7322. Min Act: -0.1700
Data Index: 2655600 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7162. Min Act: -0.1700
Data Index: 6719647 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7162. Min Act: -0.1700
Data Index: 384394 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7162. Min Act: -0.1700
Data Index: 9560297 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7002. Min Act: -0.1700
Data Index: 2471958 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7002. Min Act: -0.1700
Data Index: 9660189 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7162. Min Act: -0.1700
Data Index: 2722356 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8279. Min Range: -2.8279
Max Act: 2.7002. Min Act: -0.1700
Data Index: 7004289 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19