Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.7932. Min Act: -0.0001
Data Index: 1472927 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.5376. Min Act: -0.0001
Data Index: 1495006 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.5221. Min Act: -0.0000
Data Index: 1368836 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.4815. Min Act: -0.0001
Data Index: 1455959 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.6118. Min Act: -0.0001
Data Index: 1619496 (Python Code)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.5598. Min Act: -0.0001
Data Index: 1405007 (Python Code)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.1990. Min Act: -0.0001
Data Index: 1498223 (Python Code)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.3209. Min Act: -0.0001
Data Index: 1480240 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.5714. Min Act: -0.0001
Data Index: 1584660 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.3705. Min Act: -0.0001
Data Index: 1555052 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.2173. Min Act: -0.0001
Data Index: 1643475 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.3168. Min Act: -0.0001
Data Index: 1569945 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.4354. Min Act: -0.0001
Data Index: 1622526 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.2120. Min Act: -0.0001
Data Index: 1587242 (Python Code)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.2608. Min Act: -0.0001
Data Index: 1440321 (Python Code)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.0728. Min Act: -0.0001
Data Index: 1361181 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.3060. Min Act: -0.0001
Data Index: 1598346 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.2962. Min Act: -0.0001
Data Index: 1590034 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.4752. Min Act: -0.0001
Data Index: 1642560 (Python Code)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7932. Min Range: -2.7932
Max Act: 2.2758. Min Act: -0.0001
Data Index: 1379180 (Python Code)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19