Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3050 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.0748. Min Range: -1.0748
Max Act: 1.0748. Min Act: -0.0001
Data Index: 46358 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.8416. Min Act: -0.0001
Data Index: 640981 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.8377. Min Act: -0.0001
Data Index: 250689 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.8293. Min Act: -0.0001
Data Index: 1126900 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7081. Min Act: -0.0001
Data Index: 811772 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7598. Min Act: -0.0001
Data Index: 368612 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7789. Min Act: -0.0001
Data Index: 182151 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7930. Min Act: -0.0001
Data Index: 1125454 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7503. Min Act: -0.0001
Data Index: 1106365 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7598. Min Act: -0.0001
Data Index: 258773 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.6981. Min Act: -0.0001
Data Index: 1297774 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7371. Min Act: -0.0001
Data Index: 441 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.6438. Min Act: -0.0001
Data Index: 1336668 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.6609. Min Act: -0.0001
Data Index: 996826 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7325. Min Act: -0.0001
Data Index: 592064 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7432. Min Act: -0.0001
Data Index: 825848 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.7858. Min Act: -0.0001
Data Index: 483796 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.5925. Min Act: -0.0001
Data Index: 641775 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.6992. Min Act: -0.0001
Data Index: 380823 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0748. Min Range: -1.0748
Max Act: 0.6681. Min Act: -0.0001
Data Index: 1154075 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19