Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2122 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.8685. Min Range: -3.8685
Max Act: 3.5105. Min Act: -0.0001
Data Index: 1466950 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8685. Min Range: -3.8685
Max Act: 3.8685. Min Act: -0.0001
Data Index: 1578887 (Python Code)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8685. Min Range: -3.8685
Max Act: 3.0735. Min Act: -0.0001
Data Index: 1415255 (Python Code)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8685. Min Range: -3.8685
Max Act: 3.1840. Min Act: -0.0001
Data Index: 1608053 (Python Code)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.8797. Min Act: -0.0001
Data Index: 209034 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8685. Min Range: -3.8685
Max Act: 3.0614. Min Act: -0.0001
Data Index: 1498259 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.8877. Min Act: -0.0001
Data Index: 1401426 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.9620. Min Act: -0.0001
Data Index: 1567493 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.7612. Min Act: -0.0001
Data Index: 665542 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.8193. Min Act: -0.0001
Data Index: 257761 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.9138. Min Act: -0.0001
Data Index: 1612901 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.8690. Min Act: -0.0001
Data Index: 1543024 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.7679. Min Act: -0.0000
Data Index: 760069 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.5469. Min Act: -0.0001
Data Index: 1520416 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.5371. Min Act: -0.0001
Data Index: 1474443 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8685. Min Range: -3.8685
Max Act: 3.0061. Min Act: -0.0001
Data Index: 1407789 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.5896. Min Act: -0.0001
Data Index: 1524802 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.8115. Min Act: -0.0001
Data Index: 1583464 (Python Code)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.4200. Min Act: -0.0001
Data Index: 338067 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8685. Min Range: -3.8685
Max Act: 2.5277. Min Act: -0.0001
Data Index: 1645470 (Python Code)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19