Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2867 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.0113. Min Range: -1.0113
Max Act: 1.0113. Min Act: -0.0000
Data Index: 1769304 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.8651. Min Act: -0.0000
Data Index: 770951 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7949. Min Act: 0.0000
Data Index: 1179831 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7658. Min Act: 0.0001
Data Index: 1246900 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.8300. Min Act: -0.0000
Data Index: 391568 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7395. Min Act: -0.0000
Data Index: 1927663 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7826. Min Act: -0.0000
Data Index: 749095 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7432. Min Act: -0.0000
Data Index: 790330 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7141. Min Act: -0.0000
Data Index: 433504 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.6489. Min Act: -0.0000
Data Index: 1598365 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7152. Min Act: -0.0000
Data Index: 415649 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7087. Min Act: 0.0000
Data Index: 1946398 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7389. Min Act: -0.0000
Data Index: 1373077 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7222. Min Act: -0.0000
Data Index: 1755161 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.6859. Min Act: 0.0000
Data Index: 501710 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.6551. Min Act: 0.0001
Data Index: 1570739 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.6762. Min Act: -0.0000
Data Index: 222358 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.6554. Min Act: -0.0000
Data Index: 1243531 (The Pile)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.6604. Min Act: 0.0002
Data Index: 1539220 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0113. Min Range: -1.0113
Max Act: 0.7045. Min Act: 0.0001
Data Index: 995478 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19