Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2836 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2198. Min Range: -2.2198
Max Act: 2.2198. Min Act: -0.0001
Data Index: 308423 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.8290. Min Act: -0.0002
Data Index: 1124242 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.7608. Min Act: -0.0001
Data Index: 747474 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.6981. Min Act: -0.0001
Data Index: 150037 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.7528. Min Act: -0.0001
Data Index: 1004581 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.7760. Min Act: -0.0001
Data Index: 571711 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.6940. Min Act: -0.0001
Data Index: 209266 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.6805. Min Act: -0.0001
Data Index: 64226 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.7092. Min Act: -0.0001
Data Index: 887325 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.5443. Min Act: -0.0001
Data Index: 909927 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.5309. Min Act: -0.0001
Data Index: 1261448 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.5078. Min Act: -0.0001
Data Index: 342682 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.5493. Min Act: -0.0001
Data Index: 806804 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.5345. Min Act: -0.0002
Data Index: 975418 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.4616. Min Act: -0.0001
Data Index: 97591 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.4612. Min Act: -0.0001
Data Index: 97802 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.5706. Min Act: -0.0001
Data Index: 749041 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.3724. Min Act: -0.0001
Data Index: 425397 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.3967. Min Act: -0.0002
Data Index: 46010 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2198. Min Range: -2.2198
Max Act: 1.4779. Min Act: -0.0002
Data Index: 469477 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19