Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3375 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.9556. Min Act: -0.0001
Data Index: 976432 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0133. Min Range: -3.0133
Max Act: 3.0133. Min Act: -0.0001
Data Index: 699199 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.9650. Min Act: -0.0001
Data Index: 541240 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.7538. Min Act: -0.0001
Data Index: 1133508 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.6243. Min Act: -0.0001
Data Index: 672792 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.8067. Min Act: -0.0001
Data Index: 1336603 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.7551. Min Act: -0.0001
Data Index: 547643 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.6080. Min Act: -0.0001
Data Index: 965738 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.5206. Min Act: -0.0001
Data Index: 697340 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.4922. Min Act: -0.0001
Data Index: 708352 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.4846. Min Act: -0.0001
Data Index: 850066 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.4766. Min Act: -0.0001
Data Index: 798045 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.4892. Min Act: -0.0001
Data Index: 1227499 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.3895. Min Act: -0.0001
Data Index: 1278347 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.3884. Min Act: -0.0001
Data Index: 123597 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.3852. Min Act: -0.0001
Data Index: 851962 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.3886. Min Act: -0.0001
Data Index: 1079691 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.3736. Min Act: -0.0001
Data Index: 327157 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.3713. Min Act: -0.0001
Data Index: 1175710 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0133. Min Range: -3.0133
Max Act: 2.4781. Min Act: -0.0001
Data Index: 1088937 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19