Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2692 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.7818. Min Act: -0.0001
Data Index: 1638558 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.5316. Min Act: -0.0001
Data Index: 553472 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.6592. Min Act: -0.0000
Data Index: 641419 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.7498. Min Act: -0.0001
Data Index: 266392 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.6219. Min Act: -0.0000
Data Index: 1283445 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.6755. Min Act: -0.0000
Data Index: 1090651 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.4451. Min Act: -0.0001
Data Index: 773109 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.5126. Min Act: -0.0000
Data Index: 340809 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.7770. Min Act: -0.0001
Data Index: 1623640 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.4625. Min Act: -0.0001
Data Index: 1276009 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.7325. Min Act: -0.0001
Data Index: 1008702 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.6802. Min Act: -0.0001
Data Index: 362110 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.4625. Min Act: -0.0001
Data Index: 1135362 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.5000. Min Act: -0.0001
Data Index: 154176 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.5354. Min Act: -0.0001
Data Index: 584772 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.6433. Min Act: -0.0000
Data Index: 971383 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.4064. Min Act: -0.0000
Data Index: 469784 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.4843. Min Act: -0.0000
Data Index: 884889 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.4674. Min Act: -0.0000
Data Index: 781520 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7818. Min Range: -2.7818
Max Act: 2.3308. Min Act: -0.0001
Data Index: 1215592 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19