Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2676 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5110. Min Range: -2.5110
Max Act: 2.5110. Min Act: -0.0001
Data Index: 1489408 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5110. Min Range: -2.5110
Max Act: 2.0870. Min Act: -0.0001
Data Index: 1458522 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.8990. Min Act: -0.0001
Data Index: 1476826 (Python Code)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5110. Min Range: -2.5110
Max Act: 2.0036. Min Act: -0.0001
Data Index: 1497070 (Python Code)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.8039. Min Act: -0.0001
Data Index: 1561922 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.9164. Min Act: -0.0001
Data Index: 1504504 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.8720. Min Act: -0.0001
Data Index: 1367996 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6590. Min Act: -0.0001
Data Index: 1509990 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.7269. Min Act: -0.0001
Data Index: 1437621 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.7180. Min Act: -0.0001
Data Index: 1392111 (Python Code)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.5128. Min Act: -0.0001
Data Index: 1426296 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6673. Min Act: -0.0001
Data Index: 1456314 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6615. Min Act: -0.0001
Data Index: 1579600 (Python Code)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.5830. Min Act: -0.0001
Data Index: 1508651 (Python Code)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6629. Min Act: -0.0001
Data Index: 1524629 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6372. Min Act: -0.0001
Data Index: 1645896 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6378. Min Act: -0.0001
Data Index: 1386802 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6304. Min Act: -0.0001
Data Index: 1569632 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.7293. Min Act: -0.0001
Data Index: 1591043 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5110. Min Range: -2.5110
Max Act: 1.6104. Min Act: -0.0001
Data Index: 1467099 (Python Code)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19