Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1444 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.7979. Min Act: -0.0001
Data Index: 144880 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.8898. Min Act: -0.0001
Data Index: 1192282 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.6342. Min Act: -0.0001
Data Index: 265198 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.5843. Min Act: -0.0000
Data Index: 18867 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.5051. Min Act: -0.0001
Data Index: 519489 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.5654. Min Act: -0.0001
Data Index: 881430 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.6743. Min Act: -0.0001
Data Index: 1069996 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.4000. Min Act: -0.0000
Data Index: 1612909 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.5201. Min Act: -0.0001
Data Index: 863282 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.6491. Min Act: -0.0001
Data Index: 275093 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.7930. Min Act: -0.0001
Data Index: 1356449 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.4373. Min Act: -0.0001
Data Index: 946021 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.4414. Min Act: -0.0001
Data Index: 733500 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.2676. Min Act: -0.0001
Data Index: 1407430 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.6388. Min Act: -0.0001
Data Index: 275770 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.2044. Min Act: -0.0001
Data Index: 51423 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.2955. Min Act: -0.0001
Data Index: 415040 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.1777. Min Act: -0.0001
Data Index: 594952 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.3836. Min Act: -0.0001
Data Index: 1324555 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8898. Min Range: -2.8898
Max Act: 2.1619. Min Act: -0.0001
Data Index: 262774 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19