Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 231 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0981. Min Range: -3.0981
Max Act: 3.0981. Min Act: -0.1700
Data Index: 558907 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0981. Min Range: -3.0981
Max Act: 3.0823. Min Act: -0.1700
Data Index: 2241 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0981. Min Range: -3.0981
Max Act: 3.0192. Min Act: -0.1700
Data Index: 371795 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9876. Min Act: -0.1700
Data Index: 737452 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0981. Min Range: -3.0981
Max Act: 3.0034. Min Act: -0.1700
Data Index: 851973 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0981. Min Range: -3.0981
Max Act: 3.0034. Min Act: -0.1700
Data Index: 1299568 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9718. Min Act: -0.1700
Data Index: 913103 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9559. Min Act: -0.1700
Data Index: 1360645 (Python Code)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9718. Min Act: -0.1700
Data Index: 239866 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9559. Min Act: -0.1700
Data Index: 1293645 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9559. Min Act: -0.1700
Data Index: 860463 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9559. Min Act: -0.1700
Data Index: 661283 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9559. Min Act: -0.1700
Data Index: 1056098 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9559. Min Act: -0.1700
Data Index: 812875 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9401. Min Act: -0.1700
Data Index: 259574 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9242. Min Act: -0.1700
Data Index: 887747 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9242. Min Act: -0.1700
Data Index: 927145 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9401. Min Act: -0.1700
Data Index: 626756 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9084. Min Act: -0.1700
Data Index: 192252 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0981. Min Range: -3.0981
Max Act: 2.9242. Min Act: -0.1700
Data Index: 900205 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19