Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4504 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.9137. Min Range: -3.9137
Max Act: 3.9137. Min Act: -0.0001
Data Index: 1635585 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9137. Min Range: -3.9137
Max Act: 3.2188. Min Act: -0.0001
Data Index: 1607410 (Python Code)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9137. Min Range: -3.9137
Max Act: 3.0426. Min Act: -0.0001
Data Index: 1649888 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.9664. Min Act: -0.0001
Data Index: 1535261 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.8990. Min Act: -0.0001
Data Index: 1523870 (Python Code)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.7334. Min Act: -0.0001
Data Index: 1573780 (Python Code)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9137. Min Range: -3.9137
Max Act: 3.0723. Min Act: -0.0001
Data Index: 1596570 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.9820. Min Act: -0.0001
Data Index: 1626601 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9137. Min Range: -3.9137
Max Act: 3.0316. Min Act: -0.0001
Data Index: 1412167 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.6402. Min Act: -0.0001
Data Index: 1584132 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.9795. Min Act: -0.0001
Data Index: 1384392 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.9344. Min Act: -0.0001
Data Index: 1620379 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.8331. Min Act: -0.0001
Data Index: 1528141 (Python Code)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.8218. Min Act: -0.0001
Data Index: 1467436 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.8298. Min Act: -0.0001
Data Index: 1614434 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.6249. Min Act: -0.0001
Data Index: 1599086 (Python Code)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.8931. Min Act: -0.0001
Data Index: 1362063 (Python Code)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.7288. Min Act: -0.0001
Data Index: 1366226 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.7912. Min Act: -0.0001
Data Index: 1533642 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9137. Min Range: -3.9137
Max Act: 2.7941. Min Act: -0.0001
Data Index: 1408389 (Python Code)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19