Model: None
Dataset: The Pile
Neuron 463 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.2004. Min Range: -4.2004
Max Act: 4.2004. Min Act: -0.1700
Data Index: 10074554 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.9503. Min Act: -0.1700
Data Index: 1737321 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.9190. Min Act: -0.1700
Data Index: 9276708 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8877. Min Act: -0.1700
Data Index: 7198010 (The Pile)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8877. Min Act: -0.1700
Data Index: 5428585 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8877. Min Act: -0.1700
Data Index: 8236292 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8877. Min Act: -0.1700
Data Index: 4309957 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8564. Min Act: -0.1700
Data Index: 954785 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8408. Min Act: -0.1700
Data Index: 604104 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8408. Min Act: -0.1700
Data Index: 7943383 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8252. Min Act: -0.1700
Data Index: 9860568 (The Pile)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8095. Min Act: -0.1700
Data Index: 3365542 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8095. Min Act: -0.1700
Data Index: 1197864 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7939. Min Act: -0.1700
Data Index: 8051042 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7782. Min Act: -0.1700
Data Index: 6610740 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7782. Min Act: -0.1700
Data Index: 8806493 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7782. Min Act: -0.1700
Data Index: 4850737 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7782. Min Act: -0.1700
Data Index: 7133805 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7626. Min Act: -0.1700
Data Index: 117535 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7626. Min Act: -0.1700
Data Index: 8089146 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19