Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 812 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0660. Min Range: -2.0660
Max Act: 2.0660. Min Act: -0.0000
Data Index: 1090907 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.8745. Min Act: -0.0001
Data Index: 419586 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.2325. Min Act: -0.0001
Data Index: 1318699 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.3010. Min Act: -0.0001
Data Index: 439035 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.1265. Min Act: -0.0001
Data Index: 232380 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.1883. Min Act: -0.0001
Data Index: 838094 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.0483. Min Act: -0.0001
Data Index: 1225051 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.0772. Min Act: -0.0001
Data Index: 476522 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.0778. Min Act: -0.0001
Data Index: 996927 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9877. Min Act: -0.0001
Data Index: 692244 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.0259. Min Act: -0.0001
Data Index: 849505 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0660. Min Range: -2.0660
Max Act: 1.0120. Min Act: -0.0001
Data Index: 371322 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9172. Min Act: -0.0001
Data Index: 1215716 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.8845. Min Act: -0.0001
Data Index: 891499 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9543. Min Act: -0.0001
Data Index: 1145794 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9636. Min Act: -0.0001
Data Index: 1148844 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9287. Min Act: -0.0001
Data Index: 793527 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9775. Min Act: -0.0001
Data Index: 812781 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.9282. Min Act: -0.0001
Data Index: 412257 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0660. Min Range: -2.0660
Max Act: 0.8998. Min Act: -0.0001
Data Index: 1058979 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19