Model: None
Dataset: The Pile
Neuron 1696 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.7778. Min Act: -0.1700
Data Index: 2174343 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.7465. Min Act: -0.1700
Data Index: 6005370 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.7152. Min Act: -0.1700
Data Index: 10486882 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6839. Min Act: -0.1700
Data Index: 4927485 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 6777450 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6839. Min Act: -0.1700
Data Index: 9424048 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6839. Min Act: -0.1700
Data Index: 8792305 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 3852334 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6839. Min Act: -0.1700
Data Index: 8415790 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 7549886 (The Pile)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 5128054 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.7465. Min Act: -0.1700
Data Index: 1263524 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 3950291 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 9100129 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6839. Min Act: -0.1700
Data Index: 6606318 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 9375913 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 10454504 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 7240836 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 2485540 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7778. Min Range: -3.7778
Max Act: 3.6526. Min Act: -0.1700
Data Index: 4431956 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19