Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1058 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2851. Min Act: -0.0001
Data Index: 1158006 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2601. Min Act: -0.0001
Data Index: 1099746 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2674. Min Act: -0.0001
Data Index: 907836 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2591. Min Act: -0.0001
Data Index: 708215 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2464. Min Act: -0.0001
Data Index: 181995 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2191. Min Act: -0.0001
Data Index: 218583 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1976. Min Act: -0.0001
Data Index: 1126030 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2091. Min Act: -0.0001
Data Index: 357196 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2145. Min Act: -0.0001
Data Index: 127869 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2145. Min Act: -0.0001
Data Index: 235533 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.2014. Min Act: -0.0001
Data Index: 763093 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1946. Min Act: -0.0001
Data Index: 674141 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1894. Min Act: -0.0001
Data Index: 358984 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1759. Min Act: -0.0001
Data Index: 752858 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1947. Min Act: -0.0001
Data Index: 327073 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1941. Min Act: -0.0001
Data Index: 464670 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1772. Min Act: -0.0001
Data Index: 314807 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1774. Min Act: -0.0001
Data Index: 1300091 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1768. Min Act: -0.0001
Data Index: 660521 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2851. Min Range: -0.2851
Max Act: 0.1837. Min Act: -0.0001
Data Index: 1309876 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19