Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4966 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.2973. Min Act: -0.0001
Data Index: 1536192 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.2006. Min Act: -0.0001
Data Index: 1371896 (Python Code)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.2489. Min Act: -0.0001
Data Index: 1397042 (Python Code)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.2996. Min Act: -0.0001
Data Index: 1557912 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1733. Min Act: -0.0001
Data Index: 1651160 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0898. Min Act: -0.0001
Data Index: 1637781 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1169. Min Act: -0.0001
Data Index: 1489268 (Python Code)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1603. Min Act: -0.0001
Data Index: 1577575 (Python Code)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1932. Min Act: -0.0001
Data Index: 1483616 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1218. Min Act: -0.0001
Data Index: 1624644 (Python Code)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1996. Min Act: -0.0001
Data Index: 1492616 (Python Code)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0886. Min Act: -0.0001
Data Index: 1503382 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.1782. Min Act: -0.0001
Data Index: 1484767 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0345. Min Act: -0.0001
Data Index: 1475785 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0947. Min Act: -0.0001
Data Index: 1612439 (Python Code)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0530. Min Act: -0.0001
Data Index: 1476564 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0776. Min Act: -0.0001
Data Index: 1610303 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0069. Min Act: -0.0001
Data Index: 1568013 (Python Code)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0104. Min Act: -0.0001
Data Index: 1657036 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2996. Min Range: -1.2996
Max Act: 1.0001. Min Act: -0.0001
Data Index: 1451382 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19