Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3079 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1538. Min Range: -2.1538
Max Act: 2.1538. Min Act: -0.0001
Data Index: 1522366 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.9153. Min Act: -0.0001
Data Index: 1515962 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1398970 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.6086. Min Act: -0.0001
Data Index: 1634859 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.7850. Min Act: -0.0001
Data Index: 1522074 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.5927. Min Act: -0.0001
Data Index: 1423583 (Python Code)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.4993. Min Act: -0.0001
Data Index: 1474273 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.5703. Min Act: -0.0001
Data Index: 1449345 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.6474. Min Act: -0.0001
Data Index: 1362339 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.6193. Min Act: -0.0001
Data Index: 1421882 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.4429. Min Act: -0.0001
Data Index: 1560642 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.5835. Min Act: -0.0001
Data Index: 1400100 (Python Code)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.3987. Min Act: -0.0001
Data Index: 1405953 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.5214. Min Act: -0.0001
Data Index: 1514176 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.6425. Min Act: -0.0001
Data Index: 1609198 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.4504. Min Act: -0.0001
Data Index: 1604559 (Python Code)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.3257. Min Act: -0.0001
Data Index: 1628222 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.4269. Min Act: -0.0001
Data Index: 1510836 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.4125. Min Act: -0.0001
Data Index: 1503050 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1538. Min Range: -2.1538
Max Act: 1.4115. Min Act: -0.0001
Data Index: 1527249 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19