Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1597 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.6767. Min Act: -0.0001
Data Index: 323154 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.1905. Min Act: -0.0001
Data Index: 873191 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.3167. Min Act: -0.0001
Data Index: 194540 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.1106. Min Act: -0.0001
Data Index: 1189288 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.1030. Min Act: -0.0001
Data Index: 961067 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9894. Min Act: -0.0001
Data Index: 817113 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.0363. Min Act: -0.0001
Data Index: 754799 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9694. Min Act: -0.0001
Data Index: 56448 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9482. Min Act: -0.0001
Data Index: 709807 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.0132. Min Act: -0.0001
Data Index: 497523 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.8873. Min Act: -0.0001
Data Index: 1206674 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6767. Min Range: -2.6767
Max Act: 2.0068. Min Act: -0.0001
Data Index: 504123 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9516. Min Act: -0.0001
Data Index: 1255547 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9931. Min Act: -0.0001
Data Index: 235202 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9827. Min Act: -0.0001
Data Index: 82420 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9849. Min Act: -0.0001
Data Index: 162483 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9706. Min Act: -0.0001
Data Index: 208389 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9257. Min Act: -0.0001
Data Index: 74074 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.8638. Min Act: -0.0001
Data Index: 765 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6767. Min Range: -2.6767
Max Act: 1.9181. Min Act: -0.0001
Data Index: 278391 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19