Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3122 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0123. Min Range: -2.0123
Max Act: 2.0123. Min Act: -0.0001
Data Index: 822095 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.8680. Min Act: -0.0001
Data Index: 106292 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.8336. Min Act: -0.0001
Data Index: 307323 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.7876. Min Act: -0.0001
Data Index: 879174 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.6020. Min Act: -0.0001
Data Index: 21543 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.6740. Min Act: -0.0001
Data Index: 317540 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.8070. Min Act: -0.0001
Data Index: 761839 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.7885. Min Act: -0.0001
Data Index: 175763 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.6920. Min Act: -0.0001
Data Index: 701711 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5804. Min Act: -0.0001
Data Index: 1304425 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5807. Min Act: -0.0001
Data Index: 639719 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5616. Min Act: -0.0001
Data Index: 704275 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.6054. Min Act: -0.0001
Data Index: 219725 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5051. Min Act: -0.0001
Data Index: 858844 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5016. Min Act: -0.0001
Data Index: 780564 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5275. Min Act: -0.0001
Data Index: 610822 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5542. Min Act: -0.0001
Data Index: 942165 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5474. Min Act: -0.0001
Data Index: 1257037 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.6802. Min Act: -0.0001
Data Index: 322467 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.5235. Min Act: -0.0001
Data Index: 1143904 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19