Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2599 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1638. Min Range: -3.1638
Max Act: 3.1638. Min Act: -0.0001
Data Index: 1603592 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.9849. Min Act: -0.0001
Data Index: 1408409 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1638. Min Range: -3.1638
Max Act: 3.1051. Min Act: -0.0001
Data Index: 1494487 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.9332. Min Act: -0.0001
Data Index: 1592460 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.8537. Min Act: -0.0001
Data Index: 1427345 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1638. Min Range: -3.1638
Max Act: 3.0469. Min Act: -0.0001
Data Index: 1486721 (Python Code)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.8302. Min Act: -0.0001
Data Index: 1395280 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.9223. Min Act: -0.0001
Data Index: 1564582 (Python Code)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.8500. Min Act: -0.0001
Data Index: 1382561 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.7070. Min Act: -0.0001
Data Index: 1604178 (Python Code)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.8228. Min Act: -0.0001
Data Index: 1421040 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.5574. Min Act: -0.0001
Data Index: 1405946 (Python Code)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.6865. Min Act: -0.0001
Data Index: 1360092 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.5588. Min Act: -0.0001
Data Index: 1385947 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.8775. Min Act: -0.0001
Data Index: 1456192 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.4742. Min Act: -0.0001
Data Index: 1464980 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.7361. Min Act: -0.0001
Data Index: 1456842 (Python Code)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.3572. Min Act: -0.0001
Data Index: 1507721 (Python Code)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.6058. Min Act: -0.0001
Data Index: 1583990 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1638. Min Range: -3.1638
Max Act: 2.4611. Min Act: -0.0001
Data Index: 1480805 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19