Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3148 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.6918. Min Range: -4.6918
Max Act: 4.4361. Min Act: -0.0001
Data Index: 286237 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6918. Min Range: -4.6918
Max Act: 4.4122. Min Act: -0.0001
Data Index: 76503 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.9903. Min Act: -0.0001
Data Index: 855576 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6918. Min Range: -4.6918
Max Act: 4.6918. Min Act: -0.0001
Data Index: 170810 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6918. Min Range: -4.6918
Max Act: 4.0730. Min Act: -0.0001
Data Index: 1344945 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6918. Min Range: -4.6918
Max Act: 4.1231. Min Act: -0.0001
Data Index: 194340 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6918. Min Range: -4.6918
Max Act: 4.1786. Min Act: -0.0001
Data Index: 671870 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.6971. Min Act: -0.0001
Data Index: 57623 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.8566. Min Act: -0.0001
Data Index: 17982 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.9772. Min Act: -0.0001
Data Index: 1254273 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.4184. Min Act: -0.0001
Data Index: 827527 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.6050. Min Act: -0.0001
Data Index: 124096 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.7463. Min Act: -0.0001
Data Index: 307364 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.2535. Min Act: -0.0001
Data Index: 560778 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.5412. Min Act: -0.0001
Data Index: 474149 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.5365. Min Act: -0.0001
Data Index: 935815 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.4997. Min Act: -0.0001
Data Index: 913240 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.7080. Min Act: -0.0001
Data Index: 258102 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.7884. Min Act: -0.0001
Data Index: 1223620 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6918. Min Range: -4.6918
Max Act: 3.4919. Min Act: -0.0001
Data Index: 742813 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19