Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2850 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.5896. Min Act: -0.0001
Data Index: 895286 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.3201. Min Act: -0.0001
Data Index: 968354 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.2095. Min Act: -0.0001
Data Index: 514723 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1517. Min Act: -0.0001
Data Index: 343812 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1715. Min Act: -0.0001
Data Index: 1221258 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.2367. Min Act: -0.0001
Data Index: 396152 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.2274. Min Act: -0.0001
Data Index: 872767 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.3007. Min Act: -0.0001
Data Index: 1333824 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.2507. Min Act: -0.0001
Data Index: 885172 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.2064. Min Act: -0.0001
Data Index: 686748 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.2104. Min Act: -0.0001
Data Index: 621606 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1923. Min Act: -0.0001
Data Index: 1031573 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1926. Min Act: -0.0001
Data Index: 373663 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1060. Min Act: -0.0001
Data Index: 844530 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1414. Min Act: -0.0001
Data Index: 661377 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1454. Min Act: -0.0001
Data Index: 1286105 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.0497. Min Act: -0.0001
Data Index: 915185 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.1290. Min Act: -0.0001
Data Index: 564707 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.0925. Min Act: -0.0001
Data Index: 20475 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5896. Min Range: -1.5896
Max Act: 1.0785. Min Act: -0.0001
Data Index: 206595 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19