Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3843 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.5106. Min Act: -0.0001
Data Index: 543400 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.4154. Min Act: -0.0001
Data Index: 1245314 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.3884. Min Act: -0.0001
Data Index: 804960 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.3017. Min Act: -0.0001
Data Index: 233490 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2264. Min Act: -0.0001
Data Index: 189440 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2949. Min Act: -0.0001
Data Index: 1189573 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2668. Min Act: -0.0001
Data Index: 507226 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.3696. Min Act: -0.0001
Data Index: 742719 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2166. Min Act: -0.0001
Data Index: 978268 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.1827. Min Act: -0.0001
Data Index: 1135124 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.3126. Min Act: -0.0001
Data Index: 656226 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2064. Min Act: -0.0001
Data Index: 1111441 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2107. Min Act: -0.0001
Data Index: 1069257 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2012. Min Act: -0.0001
Data Index: 690913 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.1766. Min Act: -0.0001
Data Index: 425916 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.1398. Min Act: -0.0001
Data Index: 1053968 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2092. Min Act: -0.0001
Data Index: 1080652 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2401. Min Act: -0.0001
Data Index: 241424 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.2022. Min Act: -0.0001
Data Index: 760754 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5106. Min Range: -1.5106
Max Act: 1.1646. Min Act: -0.0001
Data Index: 413511 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19