Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2360 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.2886. Min Act: -0.0001
Data Index: 463212 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.5601. Min Act: -0.0001
Data Index: 898073 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.3407. Min Act: -0.0001
Data Index: 1250931 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.2319. Min Act: -0.0001
Data Index: 83067 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.1060. Min Act: -0.0001
Data Index: 1072425 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.3882. Min Act: -0.0001
Data Index: 1191857 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.1057. Min Act: -0.0001
Data Index: 939527 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0309. Min Act: -0.0001
Data Index: 338591 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0634. Min Act: -0.0001
Data Index: 928599 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5601. Min Range: -1.5601
Max Act: 0.9956. Min Act: -0.0001
Data Index: 1309692 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0822. Min Act: -0.0001
Data Index: 118355 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0567. Min Act: -0.0001
Data Index: 414190 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0682. Min Act: -0.0001
Data Index: 584773 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5601. Min Range: -1.5601
Max Act: 0.8464. Min Act: -0.0001
Data Index: 1182380 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.2105. Min Act: -0.0001
Data Index: 918789 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0225. Min Act: -0.0001
Data Index: 1036219 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0694. Min Act: -0.0001
Data Index: 1141848 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.1043. Min Act: -0.0001
Data Index: 941665 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5601. Min Range: -1.5601
Max Act: 0.9112. Min Act: -0.0001
Data Index: 1110708 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5601. Min Range: -1.5601
Max Act: 1.0148. Min Act: -0.0001
Data Index: 555910 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19