Model: None
Dataset: The Pile
Neuron 3214 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.9615. Min Act: -0.1700
Data Index: 3200567 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.9615. Min Act: -0.1700
Data Index: 7756195 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8989. Min Act: -0.1700
Data Index: 8353968 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8989. Min Act: -0.1700
Data Index: 3457423 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8989. Min Act: -0.1700
Data Index: 8561298 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8989. Min Act: -0.1700
Data Index: 5917215 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8989. Min Act: -0.1700
Data Index: 5942877 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8677. Min Act: -0.1700
Data Index: 243986 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8677. Min Act: -0.1700
Data Index: 10177212 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8677. Min Act: -0.1700
Data Index: 4032604 (The Pile)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8677. Min Act: -0.1700
Data Index: 8261582 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 159399 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 3063776 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 5047309 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 8324924 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 8105061 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 7153110 (The Pile)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 6277870 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 3591683 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9615. Min Range: -3.9615
Max Act: 3.8364. Min Act: -0.1700
Data Index: 390806 (The Pile)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19