Model: None
Dataset: The Pile
Neuron 687 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.2664. Min Act: -0.1700
Data Index: 185665 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.2499. Min Act: -0.1700
Data Index: 8805557 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.2334. Min Act: -0.1694
Data Index: 10396151 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.2334. Min Act: -0.1700
Data Index: 410761 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1505. Min Act: -0.1700
Data Index: 4004048 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1837. Min Act: -0.1665
Data Index: 4372572 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1505. Min Act: -0.1700
Data Index: 3989064 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1671. Min Act: -0.1692
Data Index: 7061845 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1837. Min Act: -0.1700
Data Index: 97840 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1338. Min Act: -0.1700
Data Index: 9903847 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1505. Min Act: -0.1700
Data Index: 860240 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1837. Min Act: -0.1700
Data Index: 10211774 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1171. Min Act: -0.1700
Data Index: 7227105 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1671. Min Act: -0.1700
Data Index: 7397097 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1505. Min Act: -0.1700
Data Index: 10758907 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1171. Min Act: -0.1700
Data Index: 1608801 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1171. Min Act: -0.1700
Data Index: 6711501 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1171. Min Act: -0.1700
Data Index: 406031 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1338. Min Act: -0.1700
Data Index: 6796453 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2664. Min Range: -2.2664
Max Act: 2.1171. Min Act: -0.1582
Data Index: 9515345 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19