Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3257 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.8233. Min Act: -0.0001
Data Index: 1622903 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.7617. Min Act: -0.0001
Data Index: 1373051 (Python Code)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.7299. Min Act: -0.0001
Data Index: 1578837 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6624. Min Act: -0.0001
Data Index: 1519340 (Python Code)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.7104. Min Act: -0.0001
Data Index: 1644087 (Python Code)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6985. Min Act: -0.0001
Data Index: 1364945 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.7169. Min Act: -0.0001
Data Index: 1592443 (Python Code)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.7356. Min Act: -0.0001
Data Index: 1443927 (Python Code)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.5304. Min Act: -0.0001
Data Index: 1399655 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6690. Min Act: -0.0001
Data Index: 1543568 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6469. Min Act: -0.0001
Data Index: 1431216 (Python Code)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.5676. Min Act: -0.0001
Data Index: 1471848 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6032. Min Act: -0.0001
Data Index: 1447364 (Python Code)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.7252. Min Act: -0.0001
Data Index: 1643132 (Python Code)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.5497. Min Act: -0.0001
Data Index: 1625148 (Python Code)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.5871. Min Act: -0.0001
Data Index: 1620540 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6316. Min Act: -0.0001
Data Index: 1502170 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.4334. Min Act: -0.0001
Data Index: 1385310 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.5537. Min Act: -0.0001
Data Index: 1593787 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8233. Min Range: -1.8233
Max Act: 1.6029. Min Act: -0.0001
Data Index: 1390994 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19