Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 7 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.1709. Min Range: -1.1709
Max Act: 1.1709. Min Act: -0.0001
Data Index: 1371036 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1709. Min Range: -1.1709
Max Act: 1.0515. Min Act: -0.0001
Data Index: 1388363 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.9900. Min Act: -0.0001
Data Index: 677149 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.9522. Min Act: -0.0001
Data Index: 1023828 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.9360. Min Act: -0.0001
Data Index: 1109015 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.9581. Min Act: -0.0001
Data Index: 1382909 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.8684. Min Act: -0.0001
Data Index: 71600 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.9050. Min Act: -0.0001
Data Index: 1349484 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.8319. Min Act: -0.0001
Data Index: 680674 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.8397. Min Act: -0.0001
Data Index: 1059081 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7977. Min Act: -0.0001
Data Index: 1179410 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.8440. Min Act: -0.0001
Data Index: 1379332 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7868. Min Act: -0.0001
Data Index: 1059762 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7821. Min Act: -0.0001
Data Index: 278130 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7803. Min Act: -0.0001
Data Index: 694438 (The Pile)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7461. Min Act: -0.0001
Data Index: 213338 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7296. Min Act: -0.0001
Data Index: 871418 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.7141. Min Act: -0.0001
Data Index: 1010212 (The Pile)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.6766. Min Act: -0.0001
Data Index: 45367 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1709. Min Range: -1.1709
Max Act: 0.6815. Min Act: -0.0001
Data Index: 562911 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19