Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3886 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.1753. Min Range: -4.1753
Max Act: 4.1753. Min Act: -0.0001
Data Index: 546289 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1753. Min Range: -4.1753
Max Act: 4.0768. Min Act: -0.0001
Data Index: 55919 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.9178. Min Act: -0.0001
Data Index: 480169 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.9705. Min Act: -0.0001
Data Index: 427584 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.8302. Min Act: -0.0001
Data Index: 160432 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6686. Min Act: -0.0001
Data Index: 1186236 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.8107. Min Act: -0.0001
Data Index: 1291555 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1753. Min Range: -4.1753
Max Act: 4.1059. Min Act: -0.0001
Data Index: 891526 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.7129. Min Act: -0.0001
Data Index: 479027 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.7016. Min Act: -0.0001
Data Index: 39677 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.7375. Min Act: -0.0001
Data Index: 969163 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.5549. Min Act: -0.0001
Data Index: 217096 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6821. Min Act: -0.0001
Data Index: 837467 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6792. Min Act: -0.0001
Data Index: 269149 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6939. Min Act: -0.0001
Data Index: 1316002 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.8411. Min Act: -0.0001
Data Index: 1313500 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6648. Min Act: -0.0001
Data Index: 959271 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.8148. Min Act: -0.0001
Data Index: 271816 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6809. Min Act: -0.0001
Data Index: 1293722 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1753. Min Range: -4.1753
Max Act: 3.6758. Min Act: -0.0001
Data Index: 844235 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19