Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4243 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.6411. Min Act: -0.0001
Data Index: 1402381 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.5838. Min Act: -0.0001
Data Index: 1411794 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.5701. Min Act: -0.0001
Data Index: 1421046 (Python Code)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.4727. Min Act: -0.0001
Data Index: 1511058 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.5412. Min Act: -0.0001
Data Index: 1386808 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.4767. Min Act: -0.0001
Data Index: 1624396 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.5531. Min Act: -0.0001
Data Index: 1468768 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.4859. Min Act: -0.0001
Data Index: 1498213 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.3577. Min Act: -0.0001
Data Index: 1511200 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.4037. Min Act: -0.0001
Data Index: 1566437 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.5715. Min Act: -0.0001
Data Index: 1557258 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.3645. Min Act: -0.0001
Data Index: 1530146 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.3969. Min Act: -0.0001
Data Index: 1361903 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.2969. Min Act: -0.0001
Data Index: 1602854 (Python Code)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.3840. Min Act: -0.0001
Data Index: 1586978 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.4147. Min Act: -0.0001
Data Index: 1371952 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.3082. Min Act: -0.0001
Data Index: 1616879 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.4593. Min Act: -0.0001
Data Index: 1602299 (Python Code)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.3737. Min Act: -0.0001
Data Index: 1509658 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6411. Min Range: -1.6411
Max Act: 1.2646. Min Act: -0.0001
Data Index: 1640068 (Python Code)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19