Model: None
Dataset: The Pile
Neuron 22 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.2648. Min Act: -0.1700
Data Index: 6587915 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.2812. Min Act: -0.1700
Data Index: 2321597 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.2317. Min Act: -0.1700
Data Index: 3591021 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.2483. Min Act: -0.1700
Data Index: 2892823 (The Pile)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1986. Min Act: -0.1700
Data Index: 8504841 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1986. Min Act: -0.1700
Data Index: 9580380 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.2152. Min Act: -0.1700
Data Index: 7105288 (The Pile)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1986. Min Act: -0.1700
Data Index: 5254282 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1654. Min Act: -0.1700
Data Index: 1247432 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1986. Min Act: -0.1700
Data Index: 4449428 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1820. Min Act: -0.1700
Data Index: 7059722 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1820. Min Act: -0.1700
Data Index: 1591036 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1654. Min Act: -0.1700
Data Index: 9024568 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1488. Min Act: -0.1700
Data Index: 300684 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1488. Min Act: -0.1700
Data Index: 7806959 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1488. Min Act: -0.1700
Data Index: 2559631 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1820. Min Act: -0.1700
Data Index: 5999834 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1654. Min Act: -0.1700
Data Index: 2089890 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1654. Min Act: -0.1700
Data Index: 7589903 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2812. Min Range: -2.2812
Max Act: 2.1654. Min Act: -0.1700
Data Index: 9808526 (The Pile)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19