Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1905 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1346. Min Act: -0.0001
Data Index: 259758 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.2538. Min Act: -0.0001
Data Index: 1556342 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1501. Min Act: -0.0001
Data Index: 501052 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1138. Min Act: -0.0001
Data Index: 293940 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1377. Min Act: -0.0001
Data Index: 1251042 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1261. Min Act: -0.0001
Data Index: 1409842 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0286. Min Act: -0.0001
Data Index: 978207 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2538. Min Range: -1.2538
Max Act: 0.9572. Min Act: -0.0001
Data Index: 199809 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2538. Min Range: -1.2538
Max Act: 0.9671. Min Act: -0.0001
Data Index: 1313035 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1846. Min Act: -0.0001
Data Index: 961109 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0461. Min Act: -0.0001
Data Index: 1331829 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0981. Min Act: -0.0001
Data Index: 137808 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0611. Min Act: -0.0001
Data Index: 108018 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0611. Min Act: -0.0001
Data Index: 1065499 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0660. Min Act: -0.0001
Data Index: 64171 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2538. Min Range: -1.2538
Max Act: 0.9402. Min Act: -0.0001
Data Index: 1571913 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0416. Min Act: -0.0001
Data Index: 1455126 (The Pile)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.0066. Min Act: -0.0001
Data Index: 403107 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2538. Min Range: -1.2538
Max Act: 0.7445. Min Act: -0.0001
Data Index: 1521782 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2538. Min Range: -1.2538
Max Act: 1.1099. Min Act: -0.0001
Data Index: 1828295 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19