Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 648 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2323. Min Act: -0.0001
Data Index: 88242 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2229. Min Act: -0.0001
Data Index: 409596 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2360. Min Act: -0.0001
Data Index: 1326513 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2287. Min Act: -0.0001
Data Index: 1121567 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2057. Min Act: -0.0001
Data Index: 464056 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2025. Min Act: -0.0001
Data Index: 184151 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2157. Min Act: -0.0001
Data Index: 210923 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2155. Min Act: -0.0001
Data Index: 1613253 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2081. Min Act: -0.0001
Data Index: 104590 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2234. Min Act: -0.0001
Data Index: 1356286 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2210. Min Act: -0.0001
Data Index: 414940 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2079. Min Act: -0.0001
Data Index: 1461905 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2078. Min Act: -0.0001
Data Index: 155206 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2102. Min Act: -0.0001
Data Index: 1246367 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2096. Min Act: -0.0001
Data Index: 1047816 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.1792. Min Act: -0.0001
Data Index: 285545 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.1911. Min Act: -0.0001
Data Index: 301957 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.1989. Min Act: -0.0001
Data Index: 1159983 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.2168. Min Act: -0.0001
Data Index: 805686 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2360. Min Range: -0.2360
Max Act: 0.1967. Min Act: -0.0001
Data Index: 855744 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19