Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4046 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 5.1333. Min Range: -5.1333
Max Act: 5.1333. Min Act: -0.0001
Data Index: 804462 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.2972. Min Act: -0.0001
Data Index: 1305815 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.4563. Min Act: -0.0001
Data Index: 743707 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.2692. Min Act: -0.0001
Data Index: 1218185 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.1872. Min Act: -0.0001
Data Index: 639925 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.0244. Min Act: -0.0001
Data Index: 1230935 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.4805. Min Act: -0.0001
Data Index: 563503 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.2468. Min Act: -0.0001
Data Index: 351544 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1333. Min Range: -5.1333
Max Act: 3.9590. Min Act: -0.0001
Data Index: 542669 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.3078. Min Act: -0.0001
Data Index: 1325539 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.4530. Min Act: -0.0001
Data Index: 628728 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.1026. Min Act: -0.0001
Data Index: 1290000 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1333. Min Range: -5.1333
Max Act: 3.7443. Min Act: -0.0001
Data Index: 473454 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1333. Min Range: -5.1333
Max Act: 3.9242. Min Act: -0.0001
Data Index: 791713 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.2219. Min Act: -0.0001
Data Index: 744192 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.0630. Min Act: -0.0001
Data Index: 87055 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1333. Min Range: -5.1333
Max Act: 4.0939. Min Act: -0.0001
Data Index: 912668 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1333. Min Range: -5.1333
Max Act: 3.8524. Min Act: -0.0001
Data Index: 254933 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1333. Min Range: -5.1333
Max Act: 3.7894. Min Act: -0.0001
Data Index: 139944 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1333. Min Range: -5.1333
Max Act: 3.7741. Min Act: -0.0001
Data Index: 1075140 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19