Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2951 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.9783. Min Act: -0.0001
Data Index: 208348 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.8160. Min Act: -0.0001
Data Index: 1473474 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.5983. Min Act: -0.0001
Data Index: 1389928 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.8313. Min Act: -0.0001
Data Index: 3945 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.5648. Min Act: -0.0001
Data Index: 920994 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.7365. Min Act: -0.0001
Data Index: 1529973 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.5286. Min Act: -0.0001
Data Index: 1506011 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.5802. Min Act: -0.0001
Data Index: 735353 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.5423. Min Act: -0.0001
Data Index: 1374581 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.4127. Min Act: -0.0001
Data Index: 687606 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.4937. Min Act: -0.0001
Data Index: 1380153 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.4915. Min Act: -0.0001
Data Index: 1381629 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.3850. Min Act: -0.0001
Data Index: 1436365 (Python Code)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.2495. Min Act: -0.0001
Data Index: 1452803 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.4090. Min Act: -0.0001
Data Index: 1437102 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.3976. Min Act: -0.0001
Data Index: 1408751 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.2775. Min Act: -0.0001
Data Index: 1388035 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.4066. Min Act: -0.0001
Data Index: 380028 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.4066. Min Act: -0.0001
Data Index: 280262 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9783. Min Range: -2.9783
Max Act: 2.2997. Min Act: -0.0001
Data Index: 525237 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19