Model: None
Dataset: The Pile
Neuron 1634 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.5011. Min Range: -4.5011
Max Act: 3.8915. Min Act: -0.1686
Data Index: 8981648 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.0635. Min Act: -0.1697
Data Index: 9844581 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.5011. Min Act: -0.1341
Data Index: 8265654 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.2823. Min Act: -0.1699
Data Index: 4591522 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.2198. Min Act: -0.1561
Data Index: 1125297 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.3292. Min Act: -0.1497
Data Index: 2168001 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.4698. Min Act: -0.1700
Data Index: 2056152 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.4386. Min Act: -0.1699
Data Index: 2570896 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.0166. Min Act: -0.1662
Data Index: 7615916 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.4073. Min Act: -0.1657
Data Index: 8788843 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5011. Min Range: -4.5011
Max Act: 3.9384. Min Act: -0.1651
Data Index: 117843 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.0791. Min Act: -0.1671
Data Index: 2585923 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.2042. Min Act: -0.1700
Data Index: 8813044 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.3917. Min Act: -0.1699
Data Index: 8308495 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.1417. Min Act: -0.1700
Data Index: 4107003 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.2823. Min Act: -0.1698
Data Index: 158408 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.4230. Min Act: -0.1690
Data Index: 2258048 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.0791. Min Act: -0.1432
Data Index: 68466 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5011. Min Range: -4.5011
Max Act: 3.4219. Min Act: -0.1699
Data Index: 9794291 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5011. Min Range: -4.5011
Max Act: 4.0166. Min Act: -0.1699
Data Index: 1259916 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19