Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1442 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0566. Min Act: -0.0000
Data Index: 1017170 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0544. Min Act: -0.0000
Data Index: 120858 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0527. Min Act: -0.0000
Data Index: 1590744 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0526. Min Act: 0.0000
Data Index: 1042246 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0520. Min Act: 0.0000
Data Index: 1708568 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0519. Min Act: -0.0000
Data Index: 1392551 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0519. Min Act: -0.0001
Data Index: 1978440 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0515. Min Act: -0.0000
Data Index: 1192175 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0515. Min Act: 0.0000
Data Index: 948395 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0514. Min Act: -0.0000
Data Index: 1323428 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0513. Min Act: 0.0000
Data Index: 1228905 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0507. Min Act: -0.0000
Data Index: 1081914 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0504. Min Act: 0.0000
Data Index: 406201 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0503. Min Act: -0.0000
Data Index: 1542598 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0501. Min Act: 0.0000
Data Index: 1570567 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0498. Min Act: 0.0000
Data Index: 411166 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0495. Min Act: 0.0000
Data Index: 1517711 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0495. Min Act: 0.0000
Data Index: 988665 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0493. Min Act: -0.0000
Data Index: 257453 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0566. Min Range: -0.0566
Max Act: 0.0493. Min Act: -0.0000
Data Index: 1164794 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19