Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1321 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.6510. Min Act: -0.0000
Data Index: 696892 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.3461. Min Act: -0.0000
Data Index: 889824 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.3032. Min Act: -0.0000
Data Index: 986991 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.2539. Min Act: -0.0000
Data Index: 1542534 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.1938. Min Act: -0.0000
Data Index: 1436995 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.1921. Min Act: -0.0000
Data Index: 804714 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.0333. Min Act: -0.0000
Data Index: 992681 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.1094. Min Act: -0.0000
Data Index: 1747953 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.0709. Min Act: -0.0000
Data Index: 593514 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6510. Min Range: -2.6510
Max Act: 2.1226. Min Act: -0.0000
Data Index: 684623 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.8438. Min Act: -0.0000
Data Index: 1989781 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.9428. Min Act: -0.0000
Data Index: 1854167 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.7983. Min Act: -0.0000
Data Index: 790791 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.8644. Min Act: -0.0000
Data Index: 1137174 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.7563. Min Act: -0.0000
Data Index: 7033 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.7528. Min Act: -0.0000
Data Index: 649746 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.7910. Min Act: -0.0000
Data Index: 1841283 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.7768. Min Act: -0.0000
Data Index: 1759420 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.6667. Min Act: -0.0000
Data Index: 1633539 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6510. Min Range: -2.6510
Max Act: 1.7539. Min Act: -0.0000
Data Index: 292416 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19