Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2576 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.4229. Min Act: -0.0001
Data Index: 1209387 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.4120. Min Act: -0.0001
Data Index: 631637 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.1820. Min Act: -0.0001
Data Index: 643481 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.1215. Min Act: -0.0001
Data Index: 235285 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.1122. Min Act: -0.0001
Data Index: 755412 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.1949. Min Act: -0.0001
Data Index: 1114231 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.1441. Min Act: -0.0001
Data Index: 160203 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.1433. Min Act: -0.0001
Data Index: 1571336 (Python Code)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.0878. Min Act: -0.0001
Data Index: 1162487 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9931. Min Act: -0.0001
Data Index: 287200 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9565. Min Act: -0.0001
Data Index: 97392 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.0197. Min Act: -0.0001
Data Index: 495362 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.0748. Min Act: -0.0001
Data Index: 1245551 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9668. Min Act: -0.0001
Data Index: 705239 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9549. Min Act: -0.0001
Data Index: 1161646 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9538. Min Act: -0.0001
Data Index: 899221 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4229. Min Range: -1.4229
Max Act: 1.0019. Min Act: -0.0001
Data Index: 1079696 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9210. Min Act: -0.0001
Data Index: 1126206 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9284. Min Act: -0.0001
Data Index: 201034 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4229. Min Range: -1.4229
Max Act: 0.9151. Min Act: -0.0001
Data Index: 70829 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19