Model: None
Dataset: The Pile
Neuron 2027 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.8803. Min Act: -0.1700
Data Index: 6394424 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 2524716 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6770. Min Act: -0.1700
Data Index: 3606535 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5360. Min Act: -0.1700
Data Index: 3612966 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6143. Min Act: -0.1700
Data Index: 7755289 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7395. Min Act: -0.1700
Data Index: 2956936 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.4107. Min Act: -0.1700
Data Index: 760655 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6770. Min Act: -0.1700
Data Index: 8380198 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 10668429 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5047. Min Act: -0.1700
Data Index: 8863765 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5047. Min Act: -0.1700
Data Index: 2349161 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.4890. Min Act: -0.1700
Data Index: 1738540 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6143. Min Act: -0.1700
Data Index: 4402126 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5830. Min Act: -0.1700
Data Index: 5272347 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.2694. Min Act: -0.1700
Data Index: 3921963 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 8856523 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6143. Min Act: -0.1700
Data Index: 9199653 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6926. Min Act: -0.1700
Data Index: 8494791 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6143. Min Act: -0.1700
Data Index: 3730860 (The Pile)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.3322. Min Act: -0.1700
Data Index: 3783094 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19