Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1541 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.1821. Min Act: -0.1700
Data Index: 59715 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.1322. Min Act: -0.1700
Data Index: 1026232 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.1155. Min Act: -0.1700
Data Index: 949320 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 1255981 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 927769 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 45218 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0652. Min Act: -0.1700
Data Index: 659470 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 441348 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 570 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 798708 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 1238722 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 1181396 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 738577 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0484. Min Act: -0.1700
Data Index: 1088163 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0652. Min Act: -0.1700
Data Index: 452236 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0652. Min Act: -0.1700
Data Index: 58021 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0652. Min Act: -0.1700
Data Index: 188530 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 586264 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0652. Min Act: -0.1700
Data Index: 412393 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1821. Min Range: -2.1821
Max Act: 2.0820. Min Act: -0.1700
Data Index: 127081 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19