Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2676 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1242. Min Act: -0.0001
Data Index: 1273531 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1207. Min Act: -0.0001
Data Index: 209260 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1210. Min Act: -0.0001
Data Index: 650970 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1201. Min Act: -0.0001
Data Index: 489362 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1168. Min Act: -0.0001
Data Index: 724217 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1083. Min Act: -0.0001
Data Index: 124912 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1100. Min Act: -0.0001
Data Index: 922006 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1075. Min Act: -0.0001
Data Index: 148110 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1055. Min Act: -0.0001
Data Index: 904208 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1044. Min Act: -0.0001
Data Index: 884876 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1113. Min Act: -0.0001
Data Index: 1049258 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1039. Min Act: -0.0001
Data Index: 582965 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1066. Min Act: -0.0001
Data Index: 1293329 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1060. Min Act: -0.0001
Data Index: 959072 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1032. Min Act: -0.0001
Data Index: 115841 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1085. Min Act: -0.0001
Data Index: 830588 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1053. Min Act: -0.0001
Data Index: 1114420 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.0999. Min Act: -0.0001
Data Index: 962697 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.0994. Min Act: -0.0001
Data Index: 230302 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1242. Min Range: -0.1242
Max Act: 0.1025. Min Act: -0.0001
Data Index: 724076 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19