Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2002 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.8665. Min Act: -0.0001
Data Index: 1460051 (Python Code)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.8172. Min Act: -0.0001
Data Index: 1511991 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.8342. Min Act: -0.0001
Data Index: 1458124 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.8158. Min Act: -0.0001
Data Index: 1411578 (Python Code)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.8527. Min Act: -0.0001
Data Index: 1640403 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.8167. Min Act: -0.0001
Data Index: 1648447 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7396. Min Act: -0.0001
Data Index: 1382701 (Python Code)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7447. Min Act: -0.0001
Data Index: 1430003 (Python Code)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7693. Min Act: -0.0001
Data Index: 1559312 (Python Code)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7534. Min Act: -0.0001
Data Index: 1556924 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7771. Min Act: -0.0001
Data Index: 1487490 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7336. Min Act: -0.0001
Data Index: 1599845 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7569. Min Act: -0.0001
Data Index: 1414223 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7199. Min Act: -0.0001
Data Index: 1615736 (Python Code)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7142. Min Act: -0.0001
Data Index: 1606565 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7408. Min Act: -0.0001
Data Index: 1534653 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7134. Min Act: -0.0001
Data Index: 1505323 (Python Code)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.6967. Min Act: -0.0001
Data Index: 1505725 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.6938. Min Act: -0.0001
Data Index: 1512745 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8665. Min Range: -0.8665
Max Act: 0.7014. Min Act: -0.0001
Data Index: 1596008 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19