Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 37 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1030. Min Act: -0.0005
Data Index: 235177 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1177. Min Act: -0.0005
Data Index: 1104253 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1215. Min Act: -0.0005
Data Index: 558514 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1071. Min Act: -0.0005
Data Index: 459366 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1128. Min Act: -0.0005
Data Index: 1161236 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1151. Min Act: -0.0005
Data Index: 567401 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1089. Min Act: -0.0005
Data Index: 1269753 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1050. Min Act: -0.0005
Data Index: 52453 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1044. Min Act: -0.0005
Data Index: 624011 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1020. Min Act: -0.0005
Data Index: 2265 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0996. Min Act: -0.0005
Data Index: 387911 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1030. Min Act: -0.0005
Data Index: 241903 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0976. Min Act: -0.0005
Data Index: 508137 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.1037. Min Act: -0.0005
Data Index: 1123326 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0838. Min Act: -0.0004
Data Index: 535818 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0992. Min Act: -0.0005
Data Index: 361496 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0912. Min Act: -0.0005
Data Index: 153157 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0809. Min Act: -0.0005
Data Index: 1346650 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0932. Min Act: -0.0005
Data Index: 998856 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1215. Min Range: -0.1215
Max Act: 0.0936. Min Act: -0.0005
Data Index: 292948 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19