Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.9593. Min Act: -0.0001
Data Index: 112898 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.9595. Min Act: -0.0001
Data Index: 46272 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.9058. Min Act: -0.0001
Data Index: 636829 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.8396. Min Act: -0.0001
Data Index: 569577 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.8226. Min Act: -0.0001
Data Index: 1127183 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.8224. Min Act: -0.0001
Data Index: 710432 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7633. Min Act: -0.0001
Data Index: 543416 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.8336. Min Act: -0.0001
Data Index: 67606 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7772. Min Act: -0.0001
Data Index: 942425 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7627. Min Act: -0.0001
Data Index: 1078480 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7915. Min Act: -0.0001
Data Index: 380428 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7363. Min Act: -0.0001
Data Index: 343928 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7303. Min Act: -0.0001
Data Index: 523299 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.6746. Min Act: -0.0001
Data Index: 318630 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7382. Min Act: -0.0001
Data Index: 495882 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7864. Min Act: -0.0001
Data Index: 1102688 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7305. Min Act: -0.0001
Data Index: 1286937 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7382. Min Act: -0.0001
Data Index: 705226 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.7112. Min Act: -0.0001
Data Index: 481205 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9595. Min Range: -0.9595
Max Act: 0.6704. Min Act: -0.0001
Data Index: 634924 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19