Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2005 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.8766. Min Act: -0.1700
Data Index: 1353242 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.3453. Min Act: -0.1700
Data Index: 356518 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.3453. Min Act: -0.1700
Data Index: 47829 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.3453. Min Act: -0.1700
Data Index: 559089 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.2828. Min Act: -0.1700
Data Index: 1175371 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.3140. Min Act: -0.1700
Data Index: 766016 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.2515. Min Act: -0.1700
Data Index: 288955 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.2203. Min Act: -0.1700
Data Index: 547261 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.2828. Min Act: -0.1700
Data Index: 1206528 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.2828. Min Act: -0.1700
Data Index: 1051981 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1890. Min Act: -0.1700
Data Index: 747282 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.2515. Min Act: -0.1700
Data Index: 935638 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1890. Min Act: -0.1700
Data Index: 372073 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1890. Min Act: -0.1700
Data Index: 1305496 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1265. Min Act: -0.1700
Data Index: 15405 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1578. Min Act: -0.1700
Data Index: 1013581 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1578. Min Act: -0.1700
Data Index: 197168 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.0952. Min Act: -0.1700
Data Index: 227890 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1890. Min Act: -0.1700
Data Index: 1258741 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8766. Min Range: -4.8766
Max Act: 4.1578. Min Act: -0.1700
Data Index: 565532 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19