Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4048 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.7846. Min Act: -0.0001
Data Index: 687750 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6802. Min Act: -0.0001
Data Index: 892088 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.7457. Min Act: -0.0001
Data Index: 559725 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6298. Min Act: -0.0001
Data Index: 1097656 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6641. Min Act: -0.0001
Data Index: 880127 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6429. Min Act: -0.0001
Data Index: 193813 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6458. Min Act: -0.0001
Data Index: 881384 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6660. Min Act: -0.0001
Data Index: 1024404 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6436. Min Act: -0.0001
Data Index: 1464647 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6440. Min Act: -0.0001
Data Index: 79188 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5937. Min Act: -0.0001
Data Index: 942867 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5680. Min Act: -0.0001
Data Index: 227736 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6064. Min Act: -0.0001
Data Index: 1504673 (Python Code)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5595. Min Act: -0.0001
Data Index: 1014293 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5761. Min Act: -0.0001
Data Index: 1185189 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6064. Min Act: -0.0001
Data Index: 183611 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5436. Min Act: -0.0001
Data Index: 886696 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.6035. Min Act: -0.0001
Data Index: 941362 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5669. Min Act: -0.0001
Data Index: 430991 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7846. Min Range: -0.7846
Max Act: 0.5869. Min Act: -0.0001
Data Index: 713075 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19