Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2738 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.9689. Min Act: -0.0000
Data Index: 279646 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.9543. Min Act: -0.0000
Data Index: 819358 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1169. Min Range: -2.1169
Max Act: 2.1169. Min Act: -0.0000
Data Index: 947860 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8762. Min Act: -0.0000
Data Index: 1009207 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8887. Min Act: -0.0000
Data Index: 431901 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8594. Min Act: -0.0000
Data Index: 1278853 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8551. Min Act: -0.0000
Data Index: 830554 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.7616. Min Act: -0.0000
Data Index: 1324483 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8138. Min Act: -0.0000
Data Index: 723721 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1169. Min Range: -2.1169
Max Act: 2.0000. Min Act: -0.0000
Data Index: 853089 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.6953. Min Act: -0.0000
Data Index: 1932639 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.7846. Min Act: -0.0000
Data Index: 944438 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.6611. Min Act: -0.0000
Data Index: 1669224 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8498. Min Act: -0.0000
Data Index: 979762 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.7152. Min Act: -0.0000
Data Index: 490892 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.8320. Min Act: -0.0000
Data Index: 1626450 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.7164. Min Act: -0.0000
Data Index: 120999 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.6953. Min Act: -0.0000
Data Index: 319339 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.6892. Min Act: -0.0000
Data Index: 1601264 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1169. Min Range: -2.1169
Max Act: 1.5797. Min Act: -0.0000
Data Index: 1494360 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19