Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3687 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1434. Min Range: -2.1434
Max Act: 2.1434. Min Act: -0.0001
Data Index: 1500209 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1434. Min Range: -2.1434
Max Act: 2.0072. Min Act: -0.0001
Data Index: 1491747 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.8492. Min Act: -0.0001
Data Index: 1581673 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5231. Min Act: -0.0001
Data Index: 569203 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.7043. Min Act: -0.0001
Data Index: 1542100 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5458. Min Act: -0.0001
Data Index: 884792 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.6760. Min Act: -0.0001
Data Index: 931931 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.7725. Min Act: -0.0001
Data Index: 1564021 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.7044. Min Act: -0.0001
Data Index: 1585939 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.7016. Min Act: -0.0001
Data Index: 1645642 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.0232. Min Act: -0.0001
Data Index: 396723 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.7820. Min Act: -0.0001
Data Index: 1480299 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5228. Min Act: -0.0001
Data Index: 1431446 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5752. Min Act: -0.0001
Data Index: 1475908 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.6474. Min Act: -0.0001
Data Index: 1371627 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5267. Min Act: -0.0001
Data Index: 917026 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.2518. Min Act: -0.0001
Data Index: 1454557 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.6088. Min Act: -0.0001
Data Index: 1503958 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5612. Min Act: -0.0001
Data Index: 1628840 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1434. Min Range: -2.1434
Max Act: 1.5998. Min Act: -0.0001
Data Index: 1536650 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19