Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3250 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.7518. Min Act: -0.0001
Data Index: 1382158 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.7304. Min Act: -0.0001
Data Index: 1413338 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.6786. Min Act: -0.0001
Data Index: 1567778 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.7097. Min Act: -0.0001
Data Index: 1557859 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.6438. Min Act: -0.0001
Data Index: 1420955 (Python Code)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.6390. Min Act: -0.0001
Data Index: 1503678 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.6741. Min Act: -0.0001
Data Index: 1584094 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5573. Min Act: -0.0001
Data Index: 1553967 (Python Code)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.6923. Min Act: -0.0001
Data Index: 1532898 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5430. Min Act: -0.0001
Data Index: 1486073 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5156. Min Act: -0.0001
Data Index: 1516043 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5593. Min Act: -0.0001
Data Index: 1474989 (Python Code)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5098. Min Act: -0.0001
Data Index: 1455285 (Python Code)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.4844. Min Act: -0.0001
Data Index: 1581098 (Python Code)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5221. Min Act: -0.0001
Data Index: 1460096 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.4879. Min Act: -0.0001
Data Index: 1570979 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.6033. Min Act: -0.0001
Data Index: 1595195 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5157. Min Act: -0.0001
Data Index: 1477087 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.4337. Min Act: -0.0001
Data Index: 1370326 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7518. Min Range: -1.7518
Max Act: 1.5264. Min Act: -0.0001
Data Index: 1652972 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19