Model: None
Dataset: The Pile
Neuron 1632 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6803. Min Act: -0.1700
Data Index: 2745455 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6321. Min Act: -0.1700
Data Index: 6248729 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6321. Min Act: -0.1700
Data Index: 4837155 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6161. Min Act: -0.1700
Data Index: 5876392 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6000. Min Act: -0.1700
Data Index: 2990646 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6000. Min Act: -0.1700
Data Index: 1339262 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.6000. Min Act: -0.1700
Data Index: 8999904 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5839. Min Act: -0.1700
Data Index: 9892471 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5678. Min Act: -0.1700
Data Index: 4592567 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5678. Min Act: -0.1700
Data Index: 127501 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5678. Min Act: -0.1700
Data Index: 9107677 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5516. Min Act: -0.1700
Data Index: 9225080 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5516. Min Act: -0.1700
Data Index: 8573445 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 2113938 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 8127909 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 3935776 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 9018627 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 2632186 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 2592427 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6803. Min Range: -2.6803
Max Act: 2.5355. Min Act: -0.1700
Data Index: 8772826 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19