Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1042 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.6809. Min Act: -0.0001
Data Index: 1423123 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4022. Min Act: -0.0001
Data Index: 1647208 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.3204. Min Act: -0.0001
Data Index: 1466014 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.2746. Min Act: -0.0001
Data Index: 1592237 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.1030. Min Act: -0.0001
Data Index: 1564379 (Python Code)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.9605. Min Act: -0.0001
Data Index: 1635393 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.9203. Min Act: -0.0001
Data Index: 1602769 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.7573. Min Act: -0.0001
Data Index: 1644586 (Python Code)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.8480. Min Act: -0.0001
Data Index: 1413145 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.7070. Min Act: -0.0001
Data Index: 1493317 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.8401. Min Act: -0.0001
Data Index: 1509162 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.8336. Min Act: -0.0001
Data Index: 1584204 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.6585. Min Act: -0.0001
Data Index: 1407086 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.6662. Min Act: -0.0001
Data Index: 1614274 (Python Code)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.7351. Min Act: -0.0001
Data Index: 1517869 (Python Code)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.8497. Min Act: -0.0001
Data Index: 1389082 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.5826. Min Act: -0.0001
Data Index: 1567920 (Python Code)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.6931. Min Act: -0.0001
Data Index: 1564375 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.6887. Min Act: -0.0001
Data Index: 1626174 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6809. Min Range: -3.6809
Max Act: 2.5505. Min Act: -0.0001
Data Index: 1476778 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19