Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3716 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1429. Min Act: -0.0001
Data Index: 1514879 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1255. Min Act: -0.0001
Data Index: 1543084 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1893. Min Act: -0.0001
Data Index: 1655341 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.9615. Min Act: -0.0000
Data Index: 1627115 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0503. Min Act: -0.0001
Data Index: 1539694 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.9410. Min Act: -0.0001
Data Index: 1540947 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.8125. Min Act: -0.0001
Data Index: 1390785 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.2600. Min Act: -0.0001
Data Index: 1424476 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0224. Min Act: -0.0001
Data Index: 1369952 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1493. Min Act: -0.0001
Data Index: 1483535 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.8864. Min Act: -0.0001
Data Index: 1651382 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.8874. Min Act: -0.0000
Data Index: 900658 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.8803. Min Act: -0.0001
Data Index: 1490776 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.9216. Min Act: -0.0001
Data Index: 1369882 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.7597. Min Act: -0.0001
Data Index: 1469726 (Python Code)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.7975. Min Act: -0.0001
Data Index: 1504075 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.7939. Min Act: -0.0001
Data Index: 1482804 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.8922. Min Act: -0.0001
Data Index: 1475844 (Python Code)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.8923. Min Act: -0.0001
Data Index: 1534599 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2600. Min Range: -2.2600
Max Act: 1.7873. Min Act: -0.0001
Data Index: 1570982 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19