Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1841 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1110. Min Range: -1.1110
Max Act: 1.1110. Min Act: -0.0001
Data Index: 860352 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.9507. Min Act: -0.0000
Data Index: 348758 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1110. Min Range: -1.1110
Max Act: 1.0050. Min Act: -0.0001
Data Index: 753788 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.9005. Min Act: -0.0001
Data Index: 555779 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.8581. Min Act: -0.0001
Data Index: 1475108 (The Pile)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.8272. Min Act: -0.0000
Data Index: 1649392 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.8768. Min Act: -0.0001
Data Index: 1188009 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.8056. Min Act: -0.0001
Data Index: 639251 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7736. Min Act: -0.0001
Data Index: 197753 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.8517. Min Act: -0.0001
Data Index: 173704 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7511. Min Act: -0.0001
Data Index: 1119825 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7474. Min Act: -0.0001
Data Index: 1212315 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7732. Min Act: -0.0001
Data Index: 793347 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7904. Min Act: -0.0001
Data Index: 675142 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7878. Min Act: -0.0001
Data Index: 1399898 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7879. Min Act: -0.0001
Data Index: 1349048 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.8181. Min Act: -0.0000
Data Index: 417498 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7429. Min Act: -0.0001
Data Index: 80276 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7248. Min Act: -0.0000
Data Index: 148958 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1110. Min Range: -1.1110
Max Act: 0.7854. Min Act: -0.0000
Data Index: 566492 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19