Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2644 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.8501. Min Act: -0.0001
Data Index: 368295 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.8397. Min Act: -0.0001
Data Index: 679954 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.8115. Min Act: -0.0001
Data Index: 279563 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.6169. Min Act: -0.0001
Data Index: 249541 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.6124. Min Act: -0.0001
Data Index: 516028 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.8153. Min Act: -0.0001
Data Index: 634628 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.5494. Min Act: -0.0001
Data Index: 271054 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.5018. Min Act: -0.0001
Data Index: 1224771 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.4771. Min Act: -0.0001
Data Index: 48502 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.4070. Min Act: -0.0001
Data Index: 70093 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.1144. Min Act: -0.0001
Data Index: 1303809 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.3669. Min Act: -0.0001
Data Index: 1081390 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.3408. Min Act: -0.0001
Data Index: 611949 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.4449. Min Act: -0.0001
Data Index: 1267969 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.1984. Min Act: -0.0001
Data Index: 86607 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.2901. Min Act: -0.0001
Data Index: 959569 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.2710. Min Act: -0.0001
Data Index: 383425 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.0217. Min Act: -0.0001
Data Index: 57250 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9402. Min Act: -0.0001
Data Index: 981853 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.1504. Min Act: -0.0001
Data Index: 986638 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19