Model: None
Dataset: The Pile
Neuron 1950 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.3824. Min Act: -0.1700
Data Index: 8391293 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.3354. Min Act: -0.1700
Data Index: 6580665 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.3667. Min Act: -0.1700
Data Index: 5665365 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.2882. Min Act: -0.1700
Data Index: 10061479 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.3040. Min Act: -0.1700
Data Index: 340345 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.2882. Min Act: -0.1700
Data Index: 7646645 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.2725. Min Act: -0.1700
Data Index: 1578488 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1782. Min Act: -0.1700
Data Index: 6941903 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1939. Min Act: -0.1700
Data Index: 2208024 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1939. Min Act: -0.1700
Data Index: 5126499 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1624. Min Act: -0.1700
Data Index: 3573384 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1467. Min Act: -0.1700
Data Index: 4402607 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1309. Min Act: -0.1700
Data Index: 9172329 (The Pile)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1309. Min Act: -0.1700
Data Index: 2042969 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1152. Min Act: -0.1700
Data Index: 7429325 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1309. Min Act: -0.1700
Data Index: 7765800 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1152. Min Act: -0.1700
Data Index: 5395757 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1152. Min Act: -0.1700
Data Index: 5350007 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.1152. Min Act: -0.1700
Data Index: 4199779 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3824. Min Range: -3.3824
Max Act: 3.0836. Min Act: -0.1700
Data Index: 5865192 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19