Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2470 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0953. Min Act: -0.0001
Data Index: 837193 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0892. Min Act: -0.0001
Data Index: 1507239 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0900. Min Act: -0.0001
Data Index: 1146686 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0860. Min Act: -0.0001
Data Index: 442326 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0897. Min Act: -0.0001
Data Index: 511448 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0873. Min Act: -0.0001
Data Index: 1210579 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0878. Min Act: -0.0001
Data Index: 1562106 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0876. Min Act: -0.0001
Data Index: 1012629 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0845. Min Act: -0.0001
Data Index: 145074 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0874. Min Act: -0.0001
Data Index: 608219 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0830. Min Act: -0.0001
Data Index: 667292 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0815. Min Act: -0.0001
Data Index: 250486 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0848. Min Act: -0.0001
Data Index: 336241 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0845. Min Act: -0.0001
Data Index: 781533 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0836. Min Act: -0.0001
Data Index: 77450 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0841. Min Act: -0.0001
Data Index: 441299 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0901. Min Act: -0.0001
Data Index: 262636 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0832. Min Act: -0.0001
Data Index: 439025 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0821. Min Act: -0.0001
Data Index: 888045 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0953. Min Range: -0.0953
Max Act: 0.0792. Min Act: -0.0001
Data Index: 1518556 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19