Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2641 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0002. Min Act: -0.0003
Data Index: 1279981 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 410404 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 233886 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1519130 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 39018 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 82036 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 1237681 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1350844 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1634697 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1482331 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 477340 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 252827 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1366770 (Python Code)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 493261 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 352008 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 1118301 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 842003 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0003
Data Index: 881523 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1617841 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0002. Min Range: -0.0002
Max Act: 0.0001. Min Act: -0.0002
Data Index: 1590188 (Python Code)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19