Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2458 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0842. Min Range: -2.0842
Max Act: 2.0842. Min Act: -0.0001
Data Index: 688480 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0842. Min Range: -2.0842
Max Act: 2.0726. Min Act: -0.0001
Data Index: 755125 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6950. Min Act: -0.0001
Data Index: 1446843 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.8967. Min Act: -0.0001
Data Index: 102403 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.9648. Min Act: -0.0001
Data Index: 470060 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.8115. Min Act: -0.0001
Data Index: 860414 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.5967. Min Act: -0.0001
Data Index: 1045788 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.7044. Min Act: -0.0001
Data Index: 9186 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.4255. Min Act: -0.0001
Data Index: 631582 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6642. Min Act: -0.0001
Data Index: 847117 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6706. Min Act: -0.0001
Data Index: 1034458 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6829. Min Act: -0.0001
Data Index: 1311634 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6384. Min Act: -0.0001
Data Index: 1056269 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6336. Min Act: -0.0001
Data Index: 516304 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6208. Min Act: -0.0001
Data Index: 853237 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6139. Min Act: -0.0001
Data Index: 24573 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.6139. Min Act: -0.0001
Data Index: 882534 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.5077. Min Act: -0.0001
Data Index: 881673 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.5888. Min Act: -0.0001
Data Index: 1338980 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0842. Min Range: -2.0842
Max Act: 1.5304. Min Act: -0.0001
Data Index: 199213 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19