Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3140 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.6843. Min Act: -0.0001
Data Index: 1583525 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.6930. Min Act: -0.0001
Data Index: 76370 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.6997. Min Act: -0.0001
Data Index: 964194 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.5735. Min Act: -0.0001
Data Index: 1475708 (Python Code)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.6093. Min Act: -0.0001
Data Index: 1576341 (Python Code)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.5833. Min Act: -0.0001
Data Index: 1469211 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.5413. Min Act: -0.0001
Data Index: 1386743 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.5657. Min Act: -0.0001
Data Index: 1515319 (Python Code)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4444. Min Act: -0.0001
Data Index: 1572052 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4636. Min Act: -0.0001
Data Index: 1404480 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4620. Min Act: -0.0001
Data Index: 1386179 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4198. Min Act: -0.0001
Data Index: 1384484 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.5784. Min Act: -0.0001
Data Index: 1512151 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4874. Min Act: -0.0001
Data Index: 1554904 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4517. Min Act: -0.0001
Data Index: 1465251 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.3955. Min Act: -0.0001
Data Index: 1427701 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4707. Min Act: -0.0001
Data Index: 1449557 (Python Code)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.3892. Min Act: -0.0001
Data Index: 1328085 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.4359. Min Act: -0.0001
Data Index: 1511402 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6997. Min Range: -1.6997
Max Act: 1.3682. Min Act: -0.0001
Data Index: 1371344 (Python Code)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19