Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3349 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.7640. Min Act: -0.0001
Data Index: 1023084 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.4894. Min Act: -0.0001
Data Index: 316993 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.2384. Min Act: -0.0001
Data Index: 1313907 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.6727. Min Act: -0.0001
Data Index: 532451 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.1862. Min Act: -0.0001
Data Index: 990852 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.0304. Min Act: -0.0001
Data Index: 725529 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.0010. Min Act: -0.0001
Data Index: 113371 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.7685. Min Act: -0.0001
Data Index: 622793 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.9703. Min Act: -0.0001
Data Index: 439607 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.8844. Min Act: -0.0001
Data Index: 299353 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.6921. Min Act: -0.0001
Data Index: 1177311 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.8739. Min Act: -0.0001
Data Index: 183422 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.7621. Min Act: -0.0001
Data Index: 355521 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.9045. Min Act: -0.0001
Data Index: 1276913 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.6476. Min Act: -0.0001
Data Index: 230221 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.8196. Min Act: -0.0001
Data Index: 79569 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.5591. Min Act: -0.0001
Data Index: 1171771 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7640. Min Range: -2.7640
Max Act: 2.0219. Min Act: -0.0001
Data Index: 157163 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.5966. Min Act: -0.0001
Data Index: 241181 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7640. Min Range: -2.7640
Max Act: 1.7762. Min Act: -0.0001
Data Index: 47404 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19