Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2419 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 6.6439. Min Range: -6.6439
Max Act: 6.6439. Min Act: -0.0000
Data Index: 1553894 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6439. Min Range: -6.6439
Max Act: 6.4513. Min Act: -0.0000
Data Index: 251331 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.7828. Min Act: -0.0000
Data Index: 1463051 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6439. Min Range: -6.6439
Max Act: 6.2990. Min Act: -0.0000
Data Index: 1002492 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6439. Min Range: -6.6439
Max Act: 6.0595. Min Act: -0.0000
Data Index: 1476908 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.7458. Min Act: -0.0001
Data Index: 1383563 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6439. Min Range: -6.6439
Max Act: 6.0814. Min Act: -0.0000
Data Index: 1007354 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6439. Min Range: -6.6439
Max Act: 6.1599. Min Act: -0.0000
Data Index: 98414 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.7771. Min Act: -0.0000
Data Index: 177859 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.9071. Min Act: -0.0001
Data Index: 409479 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.6340. Min Act: -0.0000
Data Index: 35060 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.7677. Min Act: -0.0000
Data Index: 1585721 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.7674. Min Act: -0.0000
Data Index: 1643423 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.5292. Min Act: -0.0000
Data Index: 150735 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.7107. Min Act: -0.0000
Data Index: 1337458 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.6917. Min Act: -0.0000
Data Index: 459859 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.4956. Min Act: -0.0000
Data Index: 1129282 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.6877. Min Act: -0.0000
Data Index: 665459 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.3239. Min Act: -0.0000
Data Index: 1972974 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6439. Min Range: -6.6439
Max Act: 5.8536. Min Act: -0.0000
Data Index: 1818050 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19