Model: None
Dataset: The Pile
Neuron 805 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.7183. Min Act: -0.1700
Data Index: 1124338 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6713. Min Act: -0.1700
Data Index: 71357 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6400. Min Act: -0.1700
Data Index: 9642790 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6244. Min Act: -0.1700
Data Index: 8696801 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6244. Min Act: -0.1700
Data Index: 10716500 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6087. Min Act: -0.1700
Data Index: 1593322 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6087. Min Act: -0.1700
Data Index: 9844123 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5931. Min Act: -0.1700
Data Index: 2207767 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5774. Min Act: -0.1700
Data Index: 4042942 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5774. Min Act: -0.1700
Data Index: 2909820 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5774. Min Act: -0.1700
Data Index: 6032959 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5774. Min Act: -0.1700
Data Index: 727375 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5774. Min Act: -0.1700
Data Index: 8560971 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5618. Min Act: -0.1700
Data Index: 6732608 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5618. Min Act: -0.1700
Data Index: 1672959 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5461. Min Act: -0.1700
Data Index: 5660384 (The Pile)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5461. Min Act: -0.1700
Data Index: 8371478 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5461. Min Act: -0.1700
Data Index: 2008715 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5461. Min Act: -0.1700
Data Index: 10442843 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5304. Min Act: -0.1700
Data Index: 7123202 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19