Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1853 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.8297. Min Act: -0.0001
Data Index: 1301529 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.6975. Min Act: -0.0001
Data Index: 1286050 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.4877. Min Act: -0.0001
Data Index: 90432 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.7317. Min Act: -0.0001
Data Index: 475882 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.6135. Min Act: -0.0001
Data Index: 292635 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5977. Min Act: -0.0001
Data Index: 1597083 (Python Code)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.6905. Min Act: -0.0001
Data Index: 1205271 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5870. Min Act: -0.0001
Data Index: 60640 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5534. Min Act: -0.0001
Data Index: 475979 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.6047. Min Act: -0.0001
Data Index: 973263 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.6018. Min Act: -0.0001
Data Index: 861128 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5592. Min Act: -0.0000
Data Index: 1474020 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5906. Min Act: -0.0001
Data Index: 1112384 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.4916. Min Act: -0.0001
Data Index: 876340 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5815. Min Act: -0.0001
Data Index: 283889 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.4755. Min Act: -0.0001
Data Index: 848108 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.4621. Min Act: -0.0001
Data Index: 1078175 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5276. Min Act: -0.0001
Data Index: 164953 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5126. Min Act: -0.0001
Data Index: 270887 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8297. Min Range: -1.8297
Max Act: 1.5170. Min Act: -0.0001
Data Index: 971217 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19