Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3981 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0005. Min Act: -0.0003
Data Index: 986777 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0005. Min Act: -0.0003
Data Index: 509752 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0005. Min Act: -0.0003
Data Index: 473672 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0004. Min Act: -0.0003
Data Index: 299117 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0004. Min Act: -0.0003
Data Index: 13315 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0004. Min Act: -0.0003
Data Index: 134481 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0004. Min Act: -0.0003
Data Index: 563959 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 946149 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0002
Data Index: 1629291 (Python Code)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 732384 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 335044 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0002
Data Index: 1490213 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 1285478 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 137907 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 922374 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 329745 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 254442 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 60369 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 107483 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0005. Min Range: -0.0005
Max Act: 0.0003. Min Act: -0.0003
Data Index: 1046449 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19