Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2356 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.3511. Min Act: -0.0000
Data Index: 1985880 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.2646. Min Act: -0.0001
Data Index: 1153512 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.2481. Min Act: -0.0001
Data Index: 61028 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.2542. Min Act: -0.0001
Data Index: 172936 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1900. Min Act: -0.0001
Data Index: 1610508 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1884. Min Act: -0.0001
Data Index: 869695 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.2377. Min Act: -0.0001
Data Index: 612359 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1536. Min Act: -0.0001
Data Index: 1306590 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1796. Min Act: -0.0001
Data Index: 227715 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1850. Min Act: -0.0001
Data Index: 520867 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1230. Min Act: -0.0001
Data Index: 1250403 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1471. Min Act: -0.0001
Data Index: 1665908 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1787. Min Act: -0.0001
Data Index: 977218 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1111. Min Act: -0.0001
Data Index: 6700 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.0053. Min Act: -0.0000
Data Index: 1146976 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.2030. Min Act: -0.0001
Data Index: 590908 (The Pile)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1177. Min Act: -0.0001
Data Index: 1674955 (The Pile)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.1080. Min Act: -0.0001
Data Index: 1017225 (The Pile)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.0621. Min Act: -0.0001
Data Index: 1823762 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3511. Min Range: -1.3511
Max Act: 1.0964. Min Act: -0.0001
Data Index: 1650971 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19