Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2935 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9604. Min Act: -0.0001
Data Index: 1611201 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9533. Min Act: -0.0001
Data Index: 1396487 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9838. Min Act: -0.0001
Data Index: 1392407 (Python Code)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.5636. Min Act: -0.0001
Data Index: 1516657 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9182. Min Act: -0.0001
Data Index: 1525638 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0542. Min Range: -4.0542
Max Act: 4.0456. Min Act: -0.0001
Data Index: 1483453 (Python Code)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.7594. Min Act: -0.0001
Data Index: 1427253 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0542. Min Range: -4.0542
Max Act: 4.0542. Min Act: -0.0001
Data Index: 1474383 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8617. Min Act: -0.0001
Data Index: 1617888 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6986. Min Act: -0.0001
Data Index: 1366689 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8739. Min Act: -0.0001
Data Index: 1474271 (Python Code)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.7202. Min Act: -0.0001
Data Index: 1640617 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6998. Min Act: -0.0001
Data Index: 1403538 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6899. Min Act: -0.0001
Data Index: 1424657 (Python Code)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6789. Min Act: -0.0001
Data Index: 1485406 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0542. Min Range: -4.0542
Max Act: 4.0387. Min Act: -0.0001
Data Index: 1451921 (Python Code)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6540. Min Act: -0.0001
Data Index: 1482854 (Python Code)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8355. Min Act: -0.0001
Data Index: 1379794 (Python Code)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6610. Min Act: -0.0001
Data Index: 1385685 (Python Code)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.6316. Min Act: -0.0001
Data Index: 1580467 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19