Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3142 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.6681. Min Act: -0.0001
Data Index: 1183107 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.1220. Min Act: -0.0001
Data Index: 1136634 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.2104. Min Act: -0.0001
Data Index: 166578 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.2527. Min Act: -0.0001
Data Index: 571883 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.0724. Min Act: -0.0000
Data Index: 766253 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.0329. Min Act: -0.0001
Data Index: 419319 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.9242. Min Act: -0.0001
Data Index: 332895 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.9980. Min Act: -0.0001
Data Index: 392115 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.9433. Min Act: -0.0001
Data Index: 1003126 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.9456. Min Act: -0.0001
Data Index: 1475741 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.5135. Min Act: -0.0001
Data Index: 998407 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.9985. Min Act: -0.0001
Data Index: 1256153 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.6892. Min Act: -0.0000
Data Index: 387226 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6681. Min Range: -2.6681
Max Act: 2.1850. Min Act: -0.0001
Data Index: 744915 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.8667. Min Act: -0.0000
Data Index: 1071099 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.7030. Min Act: -0.0001
Data Index: 1101639 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.6645. Min Act: -0.0001
Data Index: 795708 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.9833. Min Act: -0.0001
Data Index: 857873 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.5112. Min Act: -0.0001
Data Index: 980293 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6681. Min Range: -2.6681
Max Act: 1.8494. Min Act: -0.0001
Data Index: 1509755 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19