Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3860 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1156. Min Range: -3.1156
Max Act: 3.1156. Min Act: -0.0001
Data Index: 1352812 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1156. Min Range: -3.1156
Max Act: 3.0109. Min Act: -0.0001
Data Index: 24368 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.6889. Min Act: -0.0001
Data Index: 621701 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.7884. Min Act: -0.0001
Data Index: 1270494 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.8563. Min Act: -0.0001
Data Index: 1192896 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.6447. Min Act: -0.0001
Data Index: 942839 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.5349. Min Act: -0.0001
Data Index: 388239 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.5206. Min Act: -0.0001
Data Index: 5021 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.4035. Min Act: -0.0001
Data Index: 868750 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.4109. Min Act: -0.0001
Data Index: 719458 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.1743. Min Act: -0.0001
Data Index: 590606 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.3773. Min Act: -0.0001
Data Index: 730055 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.2501. Min Act: -0.0001
Data Index: 560671 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.1852. Min Act: -0.0001
Data Index: 486327 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.3082. Min Act: -0.0001
Data Index: 931661 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.2549. Min Act: -0.0001
Data Index: 545787 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.0191. Min Act: -0.0001
Data Index: 638934 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.3529. Min Act: -0.0001
Data Index: 1244039 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.2400. Min Act: -0.0001
Data Index: 1017375 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1156. Min Range: -3.1156
Max Act: 2.2095. Min Act: -0.0001
Data Index: 811326 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19