Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1529 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6896. Min Range: -2.6896
Max Act: 2.6896. Min Act: -0.0001
Data Index: 613584 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6896. Min Range: -2.6896
Max Act: 2.3026. Min Act: -0.0001
Data Index: 1336589 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6896. Min Range: -2.6896
Max Act: 2.2719. Min Act: -0.0001
Data Index: 465561 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6896. Min Range: -2.6896
Max Act: 2.2608. Min Act: -0.0001
Data Index: 964755 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.9927. Min Act: -0.0001
Data Index: 891445 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6896. Min Range: -2.6896
Max Act: 2.0719. Min Act: -0.0001
Data Index: 552459 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.7866. Min Act: -0.0001
Data Index: 1638416 (Python Code)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.9411. Min Act: -0.0001
Data Index: 1159501 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.8121. Min Act: -0.0001
Data Index: 1096704 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.6362. Min Act: -0.0001
Data Index: 1416551 (Python Code)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.7802. Min Act: -0.0001
Data Index: 311442 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.7818. Min Act: -0.0001
Data Index: 751396 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.7599. Min Act: -0.0001
Data Index: 64879 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.6944. Min Act: -0.0001
Data Index: 833386 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.7679. Min Act: -0.0001
Data Index: 881985 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.7414. Min Act: -0.0001
Data Index: 202097 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.6909. Min Act: -0.0001
Data Index: 963020 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.5896. Min Act: -0.0001
Data Index: 1015832 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.5878. Min Act: -0.0001
Data Index: 827594 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6896. Min Range: -2.6896
Max Act: 1.6373. Min Act: -0.0001
Data Index: 1064955 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19